cs.SD

arXiv:2501.06478v1 Announce Type: cross Abstract: We develop automatic speech recognition (ASR) systems for stories told by Afrikaans and isiXhosa preschool children. Oral narratives provide a way to assess children's language development before they learn to read. We consider a range of prior child-speech ASR strategies to determine which is best suited to this unique setting. Using Whisper and only 5 minutes of transcribed in-domain child speech, we find that additional in-domain adult data (adult speech matching the story domain) provides the biggest improvement, especially when coupled with voice conversion. Semi-supervised learning also helps for both languages, while parameter-efficient fine-tuning helps on Afrikaans but not on isiXhosa (which is under-represented in the Whisper model). Few child-speech studies look at non-English data, and even fewer at the preschool ages of 4 and 5. Our work therefore represents a unique validation of a wide range of previous child-speech ASR strategies in an under-explored setting.

arXiv:2501.06810v1 Announce Type: cross Abstract: This paper examines how linguistic similarity affects cross-lingual phonetic representation in speech processing for low-resource languages, emphasizing effective source language selection. Previous cross-lingual research has used various source languages to enhance performance for the target low-resource language without thorough consideration of selection. Our study stands out by providing an in-depth analysis of language selection, supported by a practical approach to assess phonetic proximity among multiple language families. We investigate how within-family similarity impacts performance in multilingual training, which aids in understanding language dynamics. We also evaluate the effect of using phonologically similar languages, regardless of family. For the phoneme recognition task, utilizing phonologically similar languages consistently achieves a relative improvement of 55.6% over monolingual training, even surpassing the performance of a large-scale self-supervised learning model. Multilingual training within the same language family demonstrates that higher phonological similarity enhances performance, while lower similarity results in degraded performance compared to monolingual training.

arXiv:2501.07474v1 Announce Type: new Abstract: In modeling musical surprisal expectancy with computational methods, it has been proposed to use the information content (IC) of one-step predictions from an autoregressive model as a proxy for surprisal in symbolic music. With an appropriately chosen model, the IC of musical events has been shown to correlate with human perception of surprise and complexity aspects, including tonal and rhythmic complexity. This work investigates whether an analogous methodology can be applied to music audio. We train an autoregressive Transformer model to predict compressed latent audio representations of a pretrained autoencoder network. We verify learning effects by estimating the decrease in IC with repetitions. We investigate the mean IC of musical segment types (e.g., A or B) and find that segment types appearing later in a piece have a higher IC than earlier ones on average. We investigate the IC's relation to audio and musical features and find it correlated with timbral variations and loudness and, to a lesser extent, dissonance, rhythmic complexity, and onset density related to audio and musical features. Finally, we investigate if the IC can predict EEG responses to songs and thus model humans' surprisal in music. We provide code for our method on github.com/sonycslparis/audioic.

arXiv:2501.06474v1 Announce Type: cross Abstract: The 1st SpeechWellness Challenge (SW1) aims to advance methods for detecting suicidal risk in adolescents using speech analysis techniques. Suicide among adolescents is a critical public health issue globally. Early detection of suicidal tendencies can lead to timely intervention and potentially save lives. Traditional methods of assessment often rely on self-reporting or clinical interviews, which may not always be accessible. The SW1 challenge addresses this gap by exploring speech as a non-invasive and readily available indicator of mental health. We release the SW1 dataset which contains speech recordings from 600 adolescents aged 10-18 years. By focusing on speech generated from natural tasks, the challenge seeks to uncover patterns and markers that correlate with suicidal risk.

arXiv:2501.06530v1 Announce Type: cross Abstract: Speech enhancement (SE) aims to improve the clarity, intelligibility, and quality of speech signals for various speech enabled applications. However, air-conducted (AC) speech is highly susceptible to ambient noise, particularly in low signal-to-noise ratio (SNR) and non-stationary noise environments. Incorporating multi-modal information has shown promise in enhancing speech in such challenging scenarios. Electromyography (EMG) signals, which capture muscle activity during speech production, offer noise-resistant properties beneficial for SE in adverse conditions. Most previous EMG-based SE methods required 35 EMG channels, limiting their practicality. To address this, we propose a novel method that considers only 8-channel EMG signals with acoustic signals using a modified SEMamba network with added cross-modality modules. Our experiments demonstrate substantial improvements in speech quality and intelligibility over traditional approaches, especially in extremely low SNR settings. Notably, compared to the SE (AC) approach, our method achieves a significant PESQ gain of 0.235 under matched low SNR conditions and 0.527 under mismatched conditions, highlighting its robustness.

arXiv:2501.06727v1 Announce Type: cross Abstract: Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline and memory loss. Early detection of AD is crucial for effective intervention and treatment. In this paper, we propose a novel approach to AD detection from spontaneous speech, which incorporates pause information into language models. Our method involves encoding pause information into embeddings and integrating them into the typical transformer-based language model, enabling it to capture both semantic and temporal features of speech data. We conduct experiments on the Alzheimer's Dementia Recognition through Spontaneous Speech (ADReSS) dataset and its extension, the ADReSSo dataset, comparing our method with existing approaches. Our method achieves an accuracy of 83.1% in the ADReSSo test set. The results demonstrate the effectiveness of our approach in discriminating between AD patients and healthy individuals, highlighting the potential of pauses as a valuable indicator for AD detection. By leveraging speech analysis as a non-invasive and cost-effective tool for AD detection, our research contributes to early diagnosis and improved management of this debilitating disease.

arXiv:2501.07102v1 Announce Type: new Abstract: Intra-sentential code-switching (CS) refers to the alternation between languages that happens within a single utterance and is a significant challenge for Automatic Speech Recognition (ASR) systems. For example, when a Vietnamese speaker uses foreign proper names or specialized terms within their speech. ASR systems often struggle to accurately transcribe intra-sentential CS due to their training on monolingual data and the unpredictable nature of CS. This issue is even more pronounced for low-resource languages, where limited data availability hinders the development of robust models. In this study, we propose AdaCS, a normalization model integrates an adaptive bias attention module (BAM) into encoder-decoder network. This novel approach provides a robust solution to CS ASR in unseen domains, thereby significantly enhancing our contribution to the field. By utilizing BAM to both identify and normalize CS phrases, AdaCS enhances its adaptive capabilities with a biased list of words provided during inference. Our method demonstrates impressive performance and the ability to handle unseen CS phrases across various domains. Experiments show that AdaCS outperforms previous state-of-the-art method on Vietnamese CS ASR normalization by considerable WER reduction of 56.2% and 36.8% on the two proposed test sets.

arXiv:2501.07329v1 Announce Type: new Abstract: Spoken language understanding (SLU) is a structure prediction task in the field of speech. Recently, many works on SLU that treat it as a sequence-to-sequence task have achieved great success. However, This method is not suitable for simultaneous speech recognition and understanding. In this paper, we propose a joint speech recognition and structure learning framework (JSRSL), an end-to-end SLU model based on span, which can accurately transcribe speech and extract structured content simultaneously. We conduct experiments on name entity recognition and intent classification using the Chinese dataset AISHELL-NER and the English dataset SLURP. The results show that our proposed method not only outperforms the traditional sequence-to-sequence method in both transcription and extraction capabilities but also achieves state-of-the-art performance on the two datasets.

arXiv:2501.07557v1 Announce Type: new Abstract: Music has always been central to human culture, reflecting and shaping traditions, emotions, and societal changes. Technological advancements have transformed how music is created and consumed, influencing tastes and the music itself. In this study, we use Network Science to analyze musical complexity. Drawing on $\approx20,000$ MIDI files across six macro-genres spanning nearly four centuries, we represent each composition as a weighted directed network to study its structural properties. Our results show that Classical and Jazz compositions have higher complexity and melodic diversity than recently developed genres. However, a temporal analysis reveals a trend toward simplification, with even Classical and Jazz nearing the complexity levels of modern genres. This study highlights how digital tools and streaming platforms shape musical evolution, fostering new genres while driving homogenization and simplicity.

arXiv:2501.06320v1 Announce Type: cross Abstract: This work introduces TTS-Transducer - a novel architecture for text-to-speech, leveraging the strengths of audio codec models and neural transducers. Transducers, renowned for their superior quality and robustness in speech recognition, are employed to learn monotonic alignments and allow for avoiding using explicit duration predictors. Neural audio codecs efficiently compress audio into discrete codes, revealing the possibility of applying text modeling approaches to speech generation. However, the complexity of predicting multiple tokens per frame from several codebooks, as necessitated by audio codec models with residual quantizers, poses a significant challenge. The proposed system first uses a transducer architecture to learn monotonic alignments between tokenized text and speech codec tokens for the first codebook. Next, a non-autoregressive Transformer predicts the remaining codes using the alignment extracted from transducer loss. The proposed system is trained end-to-end. We show that TTS-Transducer is a competitive and robust alternative to contemporary TTS systems.

arXiv:2501.06282v1 Announce Type: new Abstract: Recent advancements in large language models (LLMs) and multimodal speech-text models have laid the groundwork for seamless voice interactions, enabling real-time, natural, and human-like conversations. Previous models for voice interactions are categorized as native and aligned. Native models integrate speech and text processing in one framework but struggle with issues like differing sequence lengths and insufficient pre-training. Aligned models maintain text LLM capabilities but are often limited by small datasets and a narrow focus on speech tasks. In this work, we introduce MinMo, a Multimodal Large Language Model with approximately 8B parameters for seamless voice interaction. We address the main limitations of prior aligned multimodal models. We train MinMo through multiple stages of speech-to-text alignment, text-to-speech alignment, speech-to-speech alignment, and duplex interaction alignment, on 1.4 million hours of diverse speech data and a broad range of speech tasks. After the multi-stage training, MinMo achieves state-of-the-art performance across various benchmarks for voice comprehension and generation while maintaining the capabilities of text LLMs, and also facilitates full-duplex conversation, that is, simultaneous two-way communication between the user and the system. Moreover, we propose a novel and simple voice decoder that outperforms prior models in voice generation. The enhanced instruction-following capabilities of MinMo supports controlling speech generation based on user instructions, with various nuances including emotions, dialects, and speaking rates, and mimicking specific voices. For MinMo, the speech-to-text latency is approximately 100ms, full-duplex latency is approximately 600ms in theory and 800ms in practice. The MinMo project web page is https://funaudiollm.github.io/minmo, and the code and models will be released soon.

arXiv:2501.06959v1 Announce Type: new Abstract: Music source separation demixes a piece of music into its individual sound sources (vocals, percussion, melodic instruments, etc.), a task with no simple mathematical solution. It requires deep learning methods involving training on large datasets of isolated music stems. The most commonly available datasets are made from commercial Western music, limiting the models' applications to non-Western genres like Carnatic music. Carnatic music is a live tradition, with the available multi-track recordings containing overlapping sounds and bleeds between the sources. This poses a challenge to commercially available source separation models like Spleeter and Hybrid Demucs. In this work, we introduce 'Sanidha', the first open-source novel dataset for Carnatic music, offering studio-quality, multi-track recordings with minimal to no overlap or bleed. Along with the audio files, we provide high-definition videos of the artists' performances. Additionally, we fine-tuned Spleeter, one of the most commonly used source separation models, on our dataset and observed improved SDR performance compared to fine-tuning on a pre-existing Carnatic multi-track dataset. The outputs of the fine-tuned model with 'Sanidha' are evaluated through a listening study.

arXiv:2501.06229v1 Announce Type: new Abstract: Accurate segmentation of the vocal tract from magnetic resonance imaging (MRI) data is essential for various voice and speech applications. Manual segmentation is time intensive and susceptible to errors. This study aimed to evaluate the efficacy of deep learning algorithms for automatic vocal tract segmentation from 3D MRI.

arXiv:2501.06562v1 Announce Type: cross Abstract: Self-supervised speech models (S3Ms) have become a common tool for the speech processing community, leveraging representations for downstream tasks. Clustering S3M representations yields discrete speech units (DSUs), which serve as compact representations for speech signals. DSUs are typically obtained by k-means clustering. Using DSUs often leads to strong performance in various tasks, including automatic speech recognition (ASR). However, even with the high dimensionality and redundancy of S3M representations, preprocessing S3M representations for better clustering remains unexplored, even though it can affect the quality of DSUs. In this paper, we investigate the potential of linear preprocessing methods for extracting DSUs. We evaluate standardization, principal component analysis, whitening, and independent component analysis (ICA) on DSU-based ASR benchmarks and demonstrate their effectiveness as preprocessing for k-means. We also conduct extensive analyses of their behavior, such as orthogonality or interpretability of individual components of ICA.

arXiv:2501.06394v1 Announce Type: new Abstract: Recent advancements in personalized speech generation have brought synthetic speech increasingly close to the realism of target speakers' recordings, yet multimodal speaker generation remains on the rise. This paper introduces UniSpeaker, a unified approach for multimodality-driven speaker generation. Specifically, we propose a unified voice aggregator based on KV-Former, applying soft contrastive loss to map diverse voice description modalities into a shared voice space, ensuring that the generated voice aligns more closely with the input descriptions. To evaluate multimodality-driven voice control, we build the first multimodality-based voice control (MVC) benchmark, focusing on voice suitability, voice diversity, and speech quality. UniSpeaker is evaluated across five tasks using the MVC benchmark, and the experimental results demonstrate that UniSpeaker outperforms previous modality-specific models. Speech samples are available at \url{https://UniSpeaker.github.io}.

arXiv:2501.07088v1 Announce Type: new Abstract: TTS (Text-to-Speech) document reader from Microsoft, Adobe, Apple, and OpenAI have been serviced worldwide. They provide relatively good TTS results for general plain text, but sometimes skip contents or provide unsatisfactory results for mathematical expressions. This is because most modern academic papers are written in LaTeX, and when LaTeX formulas are compiled, they are rendered as distinctive text forms within the document. However, traditional TTS document readers output only the text as it is recognized, without considering the mathematical meaning of the formulas. To address this issue, we propose MathReader, which effectively integrates OCR, a fine-tuned T5 model, and TTS. MathReader demonstrated a lower Word Error Rate (WER) than existing TTS document readers, such as Microsoft Edge and Adobe Acrobat, when processing documents containing mathematical formulas. MathReader reduced the WER from 0.510 to 0.281 compared to Microsoft Edge, and from 0.617 to 0.281 compared to Adobe Acrobat. This will significantly contribute to alleviating the inconvenience faced by users who want to listen to documents, especially those who are visually impaired. The code is available at https://github.com/hyeonsieun/MathReader.

arXiv:2501.06276v1 Announce Type: new Abstract: Speech synthesis has significantly advanced from statistical methods to deep neural network architectures, leading to various text-to-speech (TTS) models that closely mimic human speech patterns. However, capturing nuances such as emotion and style in speech synthesis is challenging. To address this challenge, we introduce an approach centered on prompt-based emotion control. The proposed architecture incorporates emotion and intensity control across multi-speakers. Furthermore, we leverage large language models (LLMs) to manipulate speech prosody while preserving linguistic content. Using embedding emotional cues, regulating intensity levels, and guiding prosodic variations with prompts, our approach infuses synthesized speech with human-like expressiveness and variability. Lastly, we demonstrate the effectiveness of our approach through a systematic exploration of the control mechanisms mentioned above.

arXiv:2501.07246v1 Announce Type: new Abstract: Large Audio-Language Models (LALMs) have demonstrated remarkable performance in tasks involving audio perception and understanding, such as speech recognition and audio captioning. However, their reasoning capabilities - critical for solving complex real-world problems - remain underexplored. In this work, we conduct the first exploration into integrating Chain-of-Thought (CoT) reasoning into LALMs to enhance their reasoning ability across auditory modalities. We evaluate representative CoT methods, analyzing their performance in both information extraction and reasoning tasks across sound, music, and speech domains. Our findings reveal that CoT methods significantly improve performance on easy and medium tasks but encounter challenges with hard tasks, where reasoning chains can confuse the model rather than improve accuracy. Additionally, we identify a positive correlation between reasoning path length and accuracy, demonstrating the potential of scaling inference for advanced instruction-following and reasoning. This study not only highlights the promise of CoT in enhancing LALM reasoning capabilities but also identifies key limitations and provides actionable directions for future research.

arXiv:2501.06514v1 Announce Type: new Abstract: Current research in audio deepfake detection is gradually transitioning from binary classification to multi-class tasks, referred as audio deepfake source tracing task. However, existing studies on source tracing consider only closed-set scenarios and have not considered the challenges posed by open-set conditions. In this paper, we define the Neural Codec Source Tracing (NCST) task, which is capable of performing open-set neural codec classification and interpretable ALM detection. Specifically, we constructed the ST-Codecfake dataset for the NCST task, which includes bilingual audio samples generated by 11 state-of-the-art neural codec methods and ALM-based out-ofdistribution (OOD) test samples. Furthermore, we establish a comprehensive source tracing benchmark to assess NCST models in open-set conditions. The experimental results reveal that although the NCST models perform well in in-distribution (ID) classification and OOD detection, they lack robustness in classifying unseen real audio. The ST-codecfake dataset and code are available.

arXiv:2501.07215v1 Announce Type: cross Abstract: Multi-channel acoustic signal processing is a well-established and powerful tool to exploit the spatial diversity between a target signal and non-target or noise sources for signal enhancement. However, the textbook solutions for optimal data-dependent spatial filtering rest on the knowledge of second-order statistical moments of the signals, which have traditionally been difficult to acquire. In this contribution, we compare model-based, purely data-driven, and hybrid approaches to parameter estimation and filtering, where the latter tries to combine the benefits of model-based signal processing and data-driven deep learning to overcome their individual deficiencies. We illustrate the underlying design principles with examples from noise reduction, source separation, and dereverberation.