2023-09-28 更新
SPGM: Prioritizing Local Features for enhanced speech separation performance
Authors:Jia Qi Yip, Shengkui Zhao, Yukun Ma, Chongjia Ni, Chong Zhang, Hao Wang, Trung Hieu Nguyen, Kun Zhou, Dianwen Ng, Eng Siong Chng, Bin Ma
Dual-path is a popular architecture for speech separation models (e.g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships. However, it has been found that inter-blocks, which comprise half a dual-path model’s parameters, contribute minimally to performance. Thus, we propose the Single-Path Global Modulation (SPGM) block to replace inter-blocks. SPGM is named after its structure consisting of a parameter-free global pooling module followed by a modulation module comprising only 2% of the model’s total parameters. The SPGM block allows all transformer layers in the model to be dedicated to local feature modelling, making the overall model single-path. SPGM achieves 22.1 dB SI-SDRi on WSJ0-2Mix and 20.4 dB SI-SDRi on Libri2Mix, exceeding the performance of Sepformer by 0.5 dB and 0.3 dB respectively and matches the performance of recent SOTA models with up to 8 times fewer parameters.
PDF
点此查看论文截图
Unsupervised Representations Improve Supervised Learning in Speech Emotion Recognition
Authors:Amirali Soltani Tehrani, Niloufar Faridani, Ramin Toosi
Speech Emotion Recognition (SER) plays a pivotal role in enhancing human-computer interaction by enabling a deeper understanding of emotional states across a wide range of applications, contributing to more empathetic and effective communication. This study proposes an innovative approach that integrates self-supervised feature extraction with supervised classification for emotion recognition from small audio segments. In the preprocessing step, to eliminate the need of crafting audio features, we employed a self-supervised feature extractor, based on the Wav2Vec model, to capture acoustic features from audio data. Then, the output featuremaps of the preprocessing step are fed to a custom designed Convolutional Neural Network (CNN)-based model to perform emotion classification. Utilizing the ShEMO dataset as our testing ground, the proposed method surpasses two baseline methods, i.e. support vector machine classifier and transfer learning of a pretrained CNN. comparing the propose method to the state-of-the-art methods in SER task indicates the superiority of the proposed method. Our findings underscore the pivotal role of deep unsupervised feature learning in elevating the landscape of SER, offering enhanced emotional comprehension in the realm of human-computer interactions.
PDF
点此查看论文截图
My Science Tutor (MyST) — A Large Corpus of Children’s Conversational Speech
Authors:Sameer S. Pradhan, Ronald A. Cole, Wayne H. Ward
This article describes the MyST corpus developed as part of the My Science Tutor project — one of the largest collections of children’s conversational speech comprising approximately 400 hours, spanning some 230K utterances across about 10.5K virtual tutor sessions by around 1.3K third, fourth and fifth grade students. 100K of all utterances have been transcribed thus far. The corpus is freely available (https://myst.cemantix.org) for non-commercial use using a creative commons license. It is also available for commercial use (https://boulderlearning.com/resources/myst-corpus/). To date, ten organizations have licensed the corpus for commercial use, and approximately 40 university and other not-for-profit research groups have downloaded the corpus. It is our hope that the corpus can be used to improve automatic speech recognition algorithms, build and evaluate conversational AI agents for education, and together help accelerate development of multimodal applications to improve children’s excitement and learning about science, and help them learn remotely.
PDF
点此查看论文截图
Attention Is All You Need For Blind Room Volume Estimation
Authors:Chunxi Wang, Maoshen Jia, Meiran Li, Changchun Bao, Wenyu Jin
In recent years, dynamic parameterization of acoustic environments has raised increasing attention in the field of audio processing. One of the key parameters that characterize the local room acoustics in isolation from orientation and directivity of sources and receivers is the geometric room volume. Convolutional neural networks (CNNs) have been widely selected as the main models for conducting blind room acoustic parameter estimation, which aims to learn a direct mapping from audio spectrograms to corresponding labels. With the recent trend of self-attention mechanisms, this paper introduces a purely attention-based model to blindly estimate room volumes based on single-channel noisy speech signals. We demonstrate the feasibility of eliminating the reliance on CNN for this task and the proposed Transformer architecture takes Gammatone magnitude spectral coefficients and phase spectrograms as inputs. To enhance the model performance given the task-specific dataset, cross-modality transfer learning is also applied. Experimental results demonstrate that the proposed model outperforms traditional CNN models across a wide range of real-world acoustics spaces, especially with the help of the dedicated pretraining and data augmentation schemes.
PDF 5 pages, 4 figures, submitted ICASSP 2024
点此查看论文截图
VoiceLDM: Text-to-Speech with Environmental Context
Authors:Yeonghyeon Lee, Inmo Yeon, Juhan Nam, Joon Son Chung
This paper presents VoiceLDM, a model designed to produce audio that accurately follows two distinct natural language text prompts: the description prompt and the content prompt. The former provides information about the overall environmental context of the audio, while the latter conveys the linguistic content. To achieve this, we adopt a text-to-audio (TTA) model based on latent diffusion models and extend its functionality to incorporate an additional content prompt as a conditional input. By utilizing pretrained contrastive language-audio pretraining (CLAP) and Whisper, VoiceLDM is trained on large amounts of real-world audio without manual annotations or transcriptions. Additionally, we employ dual classifier-free guidance to further enhance the controllability of VoiceLDM. Experimental results demonstrate that VoiceLDM is capable of generating plausible audio that aligns well with both input conditions, even surpassing the speech intelligibility of the ground truth audio on the AudioCaps test set. Furthermore, we explore the text-to-speech (TTS) and zero-shot text-to-audio capabilities of VoiceLDM and show that it achieves competitive results. Demos and code are available at https://voiceldm.github.io.
PDF Demos and code are available at https://voiceldm.github.io
点此查看论文截图
Diffusion Conditional Expectation Model for Efficient and Robust Target Speech Extraction
Authors:Leying Zhang, Yao Qian, Linfeng Yu, Heming Wang, Xinkai Wang, Hemin Yang, Long Zhou, Shujie Liu, Yanmin Qian, Michael Zeng
Target Speech Extraction (TSE) is a crucial task in speech processing that focuses on isolating the clean speech of a specific speaker from complex mixtures. While discriminative methods are commonly used for TSE, they can introduce distortion in terms of speech perception quality. On the other hand, generative approaches, particularly diffusion-based methods, can enhance speech quality perceptually but suffer from slower inference speed. We propose an efficient generative approach named Diffusion Conditional Expectation Model (DCEM) for TSE. It can handle multi- and single-speaker scenarios in both noisy and clean conditions. Additionally, we introduce Regenerate-DCEM (R-DCEM) that can regenerate and optimize speech quality based on pre-processed speech from a discriminative model. Our method outperforms conventional methods in terms of both intrusive and non-intrusive metrics and demonstrates notable strengths in inference efficiency and robustness to unseen tasks. Audio examples are available online (https://vivian556123.github.io/dcem).
PDF Submitted to ICASSP 2024
点此查看论文截图
Unsupervised Accent Adaptation Through Masked Language Model Correction Of Discrete Self-Supervised Speech Units
Authors:Jakob Poncelet, Hugo Van hamme
Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete acoustic units. We propose to correct the discovered discrete units for accented speech back to a standard pronunciation in an unsupervised manner. A masked language model is trained on discrete units from a standard accent and iteratively corrects an accented token sequence by masking unexpected cluster sequences and predicting their common variant. Small accent adapter blocks are inserted in the pre-trained model and fine-tuned by predicting the corrected clusters, which leads to an increased robustness of the pre-trained model towards a target accent, and this without supervision. We are able to improve a state-of-the-art HuBERT Large model on a downstream accented speech recognition task by altering the training regime with the proposed method.
PDF Submitted to ICASSP2024
点此查看论文截图
BiSinger: Bilingual Singing Voice Synthesis
Authors:Huali Zhou, Yueqian Lin, Yao Shi, Peng Sun, Ming Li
Although Singing Voice Synthesis (SVS) has made great strides with Text-to-Speech (TTS) techniques, multilingual singing voice modeling remains relatively unexplored. This paper presents BiSinger, a bilingual SVS system for English and Chinese Mandarin. Current systems require separate models per language and cannot accurately represent both Chinese and English, hindering code-switch SVS. To address this gap, we design a shared representation between Chinese and English singing voices, achieved by using the CMU dictionary with mapping rules. We fuse monolingual singing datasets with established singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data. Experiments affirm that our language-independent representation and incorporation of related datasets enable a single model with enhanced performance in English and code-switch SVS while maintaining Chinese song performance. Audio samples are available at https://bisinger-svs.github.io.
PDF Accepted by ASRU2023
点此查看论文截图
On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks “In-the-Wild’’
Authors:Arthur Pimentel, Heitor Guimarães, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk
Recent advances with self-supervised learning have allowed speech recognition systems to achieve state-of-the-art (SOTA) word error rates (WER) while requiring only a fraction of the labeled training data needed by its predecessors. Notwithstanding, while such models achieve SOTA performance in matched train/test conditions, their performance degrades substantially when tested in unseen conditions. To overcome this problem, strategies such as data augmentation and/or domain shift training have been explored. Available models, however, are still too large to be considered for edge speech applications on resource-constrained devices, thus model compression tools are needed. In this paper, we explore the effects that train/test mismatch conditions have on speech recognition accuracy based on compressed self-supervised speech models. In particular, we report on the effects that parameter quantization and model pruning have on speech recognition accuracy based on the so-called robust wav2vec 2.0 model under noisy, reverberant, and noise-plus-reverberation conditions.
PDF
点此查看论文截图
NoLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping
Authors:Jan Büthe, Ahmed Mustafa, Jean-Marc Valin, Karim Helwani, Michael M. Goodwin
Speech codec enhancement methods are designed to remove distortions added by speech codecs. While classical methods are very low in complexity and add zero delay, their effectiveness is rather limited. Compared to that, DNN-based methods deliver higher quality but they are typically high in complexity and/or require delay. The recently proposed Linear Adaptive Coding Enhancer (LACE) addresses this problem by combining DNNs with classical long-term/short-term postfiltering resulting in a causal low-complexity model. A short-coming of the LACE model is, however, that quality quickly saturates when the model size is scaled up. To mitigate this problem, we propose a novel adatpive temporal shaping module that adds high temporal resolution to the LACE model resulting in the Non-Linear Adaptive Coding Enhancer (NoLACE). We adapt NoLACE to enhance the Opus codec and show that NoLACE significantly outperforms both the Opus baseline and an enlarged LACE model at 6, 9 and 12 kb/s. We also show that LACE and NoLACE are well-behaved when used with an ASR system.
PDF submitted to ICASSP 2024
点此查看论文截图
Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization
Authors:Amir Hussein, Brian Yan, Antonios Anastasopoulos, Shinji Watanabe, Sanjeev Khudanpur
Incorporating longer context has been shown to benefit machine translation, but the inclusion of context in end-to-end speech translation (E2E-ST) remains under-studied. To bridge this gap, we introduce target language context in E2E-ST, enhancing coherence and overcoming memory constraints of extended audio segments. Additionally, we propose context dropout to ensure robustness to the absence of context, and further improve performance by adding speaker information. Our proposed contextual E2E-ST outperforms the isolated utterance-based E2E-ST approach. Lastly, we demonstrate that in conversational speech, contextual information primarily contributes to capturing context style, as well as resolving anaphora and named entities.
PDF
点此查看论文截图
HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
Authors:Chen Chen, Yuchen Hu, Chao-Han Huck Yang, Sabato Macro Siniscalchi, Pin-Yu Chen, Eng Siong Chng
Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance degradation when confronted with adverse conditions, as a well-trained acoustic model is sensitive to variations in the speech domain, e.g., background noise. Intuitively, humans address this issue by relying on their linguistic knowledge: the meaning of ambiguous spoken terms is usually inferred from contextual cues thereby reducing the dependency on the auditory system. Inspired by this observation, we introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction, where N-best decoding hypotheses provide informative elements for true transcription prediction. This approach is a paradigm shift from the traditional language model rescoring strategy that can only select one candidate hypothesis as the output transcription. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses and corresponding accurate transcriptions across prevalent speech domains. Given this dataset, we examine three types of error correction techniques based on LLMs with varying amounts of labeled hypotheses-transcription pairs, which gains a significant word error rate (WER) reduction. Experimental evidence demonstrates the proposed technique achieves a breakthrough by surpassing the upper bound of traditional re-ranking based methods. More surprisingly, LLM with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list. We make our results publicly accessible for reproducible pipelines with released pre-trained models, thus providing a new evaluation paradigm for ASR error correction with LLMs.
PDF Accepted to NeurIPS 2023, 24 pages. Datasets and Benchmarks Track
点此查看论文截图
Learning from Flawed Data: Weakly Supervised Automatic Speech Recognition
Authors:Dongji Gao, Hainan Xu, Desh Raj, Leibny Paola Garcia Perera, Daniel Povey, Sanjeev Khudanpur
Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform “non-verbatim” transcription, which can result in poorly trained models. In this paper, we propose Omni-temporal Classification (OTC), a novel training criterion that explicitly incorporates label uncertainties originating from such weak supervision. This allows the model to effectively learn speech-text alignments while accommodating errors present in the training transcripts. OTC extends the conventional CTC objective for imperfect transcripts by leveraging weighted finite state transducers. Through experiments conducted on the LibriSpeech and LibriVox datasets, we demonstrate that training ASR models with OTC avoids performance degradation even with transcripts containing up to 70% errors, a scenario where CTC models fail completely. Our implementation is available at https://github.com/k2-fsa/icefall.
PDF
点此查看论文截图