23 citations · 45 across the 17 of their papers we have counts for
18 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events
Xiaoyu Yang, Qiujia Li, Chao Zhang +1
With the advances in deep learning, the performance of end-to-end (E2E) single-task models for speech and audio processing has been constantly improving. However, it is still chall…
Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation
Wen Wu, Bo Li, Chao Zhang +5
The subjective perception of emotion leads to inconsistent labels from human annotators. Typically, utterances lacking majority-agreed labels are excluded when training an emotion…
Efficient Adapter Finetuning for Tail Languages in Streaming Multilingual ASR
Junwen Bai, Bo Li, Qiujia Li +2
The end-to-end ASR model is often desired in the streaming multilingual scenario since it is easier to deploy and can benefit from pre-trained speech models such as powerful founda…
Massive End-to-end Models for Short Search Queries
Weiran Wang, Rohit Prabhavalkar, Dongseong Hwang +11
In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for of…
Modular Domain Adaptation for Conformer-Based Streaming ASR
Qiujia Li, Bo Li, Dongseong Hwang +2
Speech data from different domains has distinct acoustic and linguistic characteristics. It is common to train a single multidomain model such as a Conformer transducer for speech…
Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition
Xiaoyu Yang, Qiujia Li, Chao Zhang +1
Although large foundation models pre-trained by self-supervised learning have achieved state-of-the-art performance in many tasks including automatic speech recognition (ASR), know…
Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models
Xiaoyu Yang, Qiujia Li, Philip C. Woodland
Self-supervised pre-training is an effective approach to leveraging a large amount of unlabelled data to reduce word error rates (WERs) of automatic speech recognition (ASR) system…
Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition
Qiujia Li, Yu Zhang, David Qiu +3
As end-to-end automatic speech recognition (ASR) models reach promising performance, various downstream tasks rely on good confidence estimators for these systems. Recent research…
Combining Frame-Synchronous and Label-Synchronous Systems for Speech Recognition
Qiujia Li, Chao Zhang, Philip C. Woodland
Commonly used automatic speech recognition (ASR) systems can be classified into frame-synchronous and label-synchronous categories, based on whether the speech is decoded on a per-…
Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction
David Qiu, Yanzhang He, Qiujia Li +3
Confidence scores are very useful for downstream applications of automatic speech recognition (ASR) systems. Recent works have proposed using neural networks to learn word or utter…
Learning Word-Level Confidence For Subword End-to-End ASR
David Qiu, Qiujia Li, Yanzhang He +9
We study the problem of word-level confidence estimation in subword-based end-to-end (E2E) models for automatic speech recognition (ASR). Although prior works have proposed trainin…
Residual Energy-Based Models for End-to-End Speech Recognition
Qiujia Li, Yu Zhang, Bo Li +2
End-to-end models with auto-regressive decoders have shown impressive results for automatic speech recognition (ASR). These models formulate the sequence-level probability as a pro…
Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition
Qiujia Li, David Qiu, Yu Zhang +5
For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based…
Discriminative Neural Clustering for Speaker Diarisation
Qiujia Li, Florian L. Kreyssig, Chao Zhang +1
In this paper, we propose Discriminative Neural Clustering (DNC) that formulates data clustering with a maximum number of clusters as a supervised sequence-to-sequence learning pro…
Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition
Qiujia Li, Chao Zhang, Philip C. Woodland
This paper proposes a novel automatic speech recognition (ASR) framework called Integrated Source-Channel and Attention (ISCA) that combines the advantages of traditional systems b…
Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks
Anton Ragni, Qiujia Li, Mark Gales +1
The standard approach to assess reliability of automatic speech transcriptions is through the use of confidence scores. If accurate, these scores provide a flexible mechanism to fl…
Bi-Directional Lattice Recurrent Neural Networks for Confidence Estimation
Qiujia Li, Preben Ness, Anton Ragni +1
The standard approach to mitigate errors made by an automatic speech recognition system is to use confidence scores associated with each predicted word. In the simplest case, these…