4 citations · 13 across the 15 of their papers we have counts for
17 papers
Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants
Aadam Haq, Oggi Rudovic, Malcolm Chadwick +5
AI voice assistants often use Automatic Speech Recognition (ASR) with LLM-based reasoning, yet existing systems struggle with regional British accents, including Scottish, Irish, a…
Streaming Speech-to-Text Translation with a SpeechLLM
Titouan Parcollet, Shucong Zhang, Xianrui Zheng +1
Normally, a system that translates speech into text consists of separate modules for speech recognition and text-to-text translation. Combining those tasks into a SpeechLLM promise…
Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes
Rogier C. van Dalen, Shucong Zhang, Titouan Parcollet +1
Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too litt…
Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognition
Yuan Tseng, Titouan Parcollet, Rogier van Dalen +2
Recent work suggests that large language models (LLMs) can improve performance of speech tasks compared to existing systems. To support their claims, results on LibriSpeech and Com…
Loquacious Set: 25,000 Hours of Transcribed and Diverse English Speech Recognition Data for Research and Commercial Use
Titouan Parcollet, Yuan Tseng, Shucong Zhang +1
Automatic speech recognition (ASR) research is driven by the availability of common datasets between industrial researchers and academics, encouraging comparisons and evaluations.…
Benchmarking Rotary Position Embeddings for Automatic Speech Recognition
Shucong Zhang, Titouan Parcollet, Rogier van Dalen +1
Self-attention relies on positional embeddings to encode input order. Relative Position (RelPos) embeddings are widely used in Automatic Speech Recognition (ASR). However, RelPos h…
Linear Time Complexity Conformers with SummaryMixing for Streaming Speech Recognition
Titouan Parcollet, Rogier van Dalen, Shucong Zhang +1
Automatic speech recognition (ASR) with an encoder equipped with self-attention, whether streaming or non-streaming, takes quadratic time in the length of the speech utterance. Thi…
Linear-Complexity Self-Supervised Learning for Speech Processing
Shucong Zhang, Titouan Parcollet, Rogier van Dalen +1
Self-supervised learning (SSL) models usually require weeks of pre-training with dozens of high-end GPUs. These models typically have a multi-headed self-attention (MHSA) context e…
Open-Source Conversational AI with SpeechBrain 1.0
Mirco Ravanelli, Titouan Parcollet, Adel Moumen +30
SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech recognition, speech enhancement, speaker re…
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Titouan Parcollet, Ha Nguyen, Solene Evain +19
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing…
SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding
Titouan Parcollet, Rogier van Dalen, Shucong Zhang +1
Modern speech processing systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down in…
Cross-Attention is all you need: Real-Time Streaming Transformers for Personalised Speech Enhancement
Shucong Zhang, Malcolm Chadwick, Alberto Gil C. P. Ramos +1
Personalised speech enhancement (PSE), which extracts only the speech of a target user and removes everything else from a recorded audio clip, can potentially improve users' experi…
Transformer-based Streaming ASR with Cumulative Attention
Mohan Li, Shucong Zhang, Catalin Zorila +1
In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monoton…
Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers
Shucong Zhang, Cong-Thanh Do, Rama Doddipatla +3
Although the lower layers of a deep neural network learn features which are transferable across datasets, these layers are not transferable within the same dataset. That is, in gen…
On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers
Shucong Zhang, Erfan Loweimi, Peter Bell +1
Self-attention models such as Transformers, which can capture temporal relationships without being limited by the distance between events, have given competitive speech recognition…
Stochastic Attention Head Removal: A simple and effective method for improving Transformer Based ASR Models
Shucong Zhang, Erfan Loweimi, Peter Bell +1
Recently, Transformer based models have shown competitive automatic speech recognition (ASR) performance. One key factor in the success of these models is the multi-head attention…
When Can Self-Attention Be Replaced by Feed Forward Layers?
Shucong Zhang, Erfan Loweimi, Peter Bell +1
Recently, self-attention models such as Transformers have given competitive results compared to recurrent neural network systems in speech recognition. The key factor for the outst…