8 papers
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…
DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models
Haaris Mehmood, Jie Xu, Karthikeyan Saravanan +2
Federated learning (FL) enables the collaborative training of large-scale language models (LLMs) across edge devices while keeping user data on-device. However, FL still exposes se…
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…
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.…