Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint speech-text foundational models. In this work, we present a comprehensive analysis on building ASR systems with discrete codes. We investigate different methods for codec training such as quantization schemes and time-domain vs spectral feature encodings. We further explore ASR training techniques aimed at enhancing performance, training efficiency, and noise robustness. Drawing upon our findings, we introduce a codec ASR pipeline that outperforms Encodec at similar bit-rate. Remarkably, it also surpasses the state-of-the-art results achieved by strong self-supervised models on the 143 languages ML-SUPERB benchmark despite being smaller in size and pretrained on significantly less data.
Performant ASR Models for Medical Entities in Accented Speech
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Intron Health；Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学与应用实验室）；University of Minnesota - Twin Cities（明尼苏达大学双城分校）；African Masters of Machine Intelligence（非洲机器智能硕士项目）；AIMS/AMMI（非洲数学科学研究所/非洲机器智能硕士项目）；AI Saturdays Lagos（拉各斯AI周六）；Masakhane NLP（Masakhane自然语言处理项目）
Controllable Dysarthric Speech Synthesis with Patient-Specific Conditioning for Speaker-Diverse ASR Augmentation
Department of Language Science and Technology, The Hong Kong Polytechnic University（语言科学与技术系，香港理工大学）；College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine（康复医学学院，福建中医药大学）；Department of Imaging, Rehabilitation Hospital affiliated to Fujian University of Traditional Chinese Medicine（影像科，福建中医药大学附属康复医院）
Connecting the Dots: Enduring Performance Gaps in ASR Systems Between Standard and Minority English Varieties
Koel Labs LLC（科尔实验室有限责任公司）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Toronto（多伦多大学）；University of Essex（埃塞克斯大学）；The Ohio State University（俄亥俄州立大学）
Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate representations to bridge acoustic model and vocoder, which suffers from two limitations: 1) the continuous acoustic frames are hard to predict with phoneme only, and acoustic information like duration or pitch is also needed to solve the one-to-many problem, which is not easy to scale on large scale and noise datasets; 2) to achieve diverse speech output base…
Speech data is expensive to collect, and incredibly sensitive to its sources. It is often the case that organizations independently collect small datasets for their own use, but often these are not performant for the demands of machine learning. Organizations could pool these datasets together and jointly build a strong ASR system; sharing data in the clear, however, comes with tremendous risk, in terms of intellectual property loss as well as loss of privacy of the individuals who exist in the dataset. In this paper, we offer a potential solution for learning an ML model across multiple organ…
This paper describes our NPU-ASLP system submitted to the ISCSLP 2022 Magichub Code-Switching ASR Challenge. In this challenge, we first explore several popular end-to-end ASR architectures and training strategies, including bi-encoder, language-aware encoder (LAE) and mixture of experts (MoE). To improve our system's language modeling ability, we further attempt the internal language model as well as the long context language model. Given the limited training data in the challenge, we further investigate the effects of data augmentation, including speed perturbation, pitch shifting, speech co…
Automatic speech recognition (ASR) in the cloud allows the use of larger models and more powerful multi-channel signal processing front-ends compared to on-device processing. However, it also adds an inherent latency due to the transmission of the audio signal, especially when transmitting multiple channels of a microphone array. One way to reduce the network bandwidth requirements is client-side compression with a lossy codec such as Opus. However, this compression can have a detrimental effect especially on multi-channel ASR front-ends, due to the distortion and loss of spatial information i…
