Related papers: AISHELL6-whisper: A Chinese Mandarin Audio-visual …
Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particularly for the 80 million-strong global community of people…
Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in…
Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of parameters, leading to slow inferences even with adapted hardware. In this context,…
Real-time automatic speech recognition systems are increasingly integrated into interactive applications, from voice assistants to live transcription services. However, scaling these systems to support multiple concurrent clients while…
Modern multilingual automatic speech recognition (ASR) systems like Whisper have made it possible to transcribe audio in multiple languages with a single model. However, current state-of-the-art ASR models are typically evaluated on…
Speech enhancement has recently achieved great success with various deep learning methods. However, most conventional speech enhancement systems are trained with supervised methods that impose two significant challenges. First, a majority…
Lip Reading, or Visual Automatic Speech Recognition (V-ASR), is a complex task requiring the interpretation of spoken language exclusively from visual cues, primarily lip movements and facial expressions. This task is especially challenging…
This research introduces an enhanced version of the multi-objective speech assessment model--MOSA-Net+, by leveraging the acoustic features from Whisper, a large-scaled weakly supervised model. We first investigate the effectiveness of…
In audio-driven video generation, creating Mandarin videos presents significant challenges. Collecting comprehensive Mandarin datasets is difficult, and the complex lip movements in Mandarin further complicate model training compared to…
Speech codecs serve as bridges between continuous speech signals and large language models, yet face an inherent conflict between acoustic fidelity and semantic preservation. To mitigate this conflict, prevailing methods augment acoustic…
Machine recognition of an atypical speech like whispered speech, is a challenging task. We introduce whisper-to-natural-speech conversion using sequence-to-sequence approach by proposing enhanced transformer architecture, which uses both…
State-of-the-art automatic speech recognition (ASR) models like Whisper, perform poorly on atypical speech, such as that produced by individuals with dysarthria. Past works for atypical speech have mostly investigated fully personalized (or…
We collect novel data in the public service domain to evaluate the capability of the state-of-the-art automatic speech recognition (ASR) models in capturing regional differences in accents in the United Kingdom (UK), specifically focusing…
Current Multilingual ASR models only support a fraction of the world's languages. Continual Learning (CL) aims to tackle this problem by adding new languages to pre-trained models while avoiding the loss of performance on existing…
Accurate far-field speech datasets are critical for tasks such as automatic speech recognition (ASR), dereverberation, speech enhancement, and source separation. However, current datasets are limited by the trade-off between acoustic…
Automatic Speech Recognition (ASR) and speaker diarization in Bangla remain challenging due to long form recordings, diverse acoustic conditions, and significant speaker variability. This work addresses these two core tasks in Bangla spoken…
Neural networks have been successfully used for non-intrusive speech intelligibility prediction. Recently, the use of feature representations sourced from intermediate layers of pre-trained self-supervised and weakly-supervised models has…
Separating target speech from mixed signals containing flexible speaker quantities presents a challenging task. While existing methods demonstrate strong separation performance and noise robustness, they predominantly assume prior knowledge…
Expanding the language coverage of speech technology has the potential to improve access to information for many more people. However, current speech technology is restricted to about one hundred languages which is a small fraction of the…
We propose a novel procedure to generate pseudo mandarin speech data named as CAMP (character audio mix up), which aims at generating audio from a character scale. We also raise a method for building a mandarin character scale audio…