21 citations · 42 across the 11 of their papers we have counts for
13 papers
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities
George Saon, Avihu Dekel, Alexander Brooks +21
Granite-speech LLMs are compact and efficient speech language models specifically designed for English ASR and automatic speech translation (AST). The models were trained by modali…
Robust ASR Error Correction with Conservative Data Filtering
Takuma Udagawa, Masayuki Suzuki, Masayasu Muraoka +1
Error correction (EC) based on large language models is an emerging technology to enhance the performance of automatic speech recognition (ASR) systems. Generally, training data fo…
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata +2
Transferring the knowledge of large language models (LLMs) is a promising technique to incorporate linguistic knowledge into end-to-end automatic speech recognition (ASR) systems.…
Effect and Analysis of Large-scale Language Model Rescoring on Competitive ASR Systems
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata +2
Large-scale language models (LLMs) such as GPT-2, BERT and RoBERTa have been successfully applied to ASR N-best rescoring. However, whether or how they can benefit competitive, nea…
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing
Xiaodong Cui, George Saon, Tohru Nagano +4
We introduce two techniques, length perturbation and n-best based label smoothing, to improve generalization of deep neural network (DNN) acoustic models for automatic speech recog…
Knowledge Distillation Leveraging Alternative Soft Targets from Non-Parallel Qualified Speech Data
Tohru Nagano, Takashi Fukuda, Gakuto Kurata
This paper describes a novel knowledge distillation framework that leverages acoustically qualified speech data included in an existing training data pool as privileged information…
RNN Transducer Models For Spoken Language Understanding
Samuel Thomas, Hong-Kwang J. Kuo, George Saon +5
We present a comprehensive study on building and adapting RNN transducer (RNN-T) models for spoken language understanding(SLU). These end-to-end (E2E) models are constructed in thr…
End-to-End Spoken Language Understanding Without Full Transcripts
Hong-Kwang J. Kuo, Zoltán Tüske, Samuel Thomas +7
An essential component of spoken language understanding (SLU) is slot filling: representing the meaning of a spoken utterance using semantic entity labels. In this paper, we develo…
English Broadcast News Speech Recognition by Humans and Machines
Samuel Thomas, Masayuki Suzuki, Yinghui Huang +8
With recent advances in deep learning, considerable attention has been given to achieving automatic speech recognition performance close to human performance on tasks like conversa…
Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation
Gakuto Kurata, Kartik Audhkhasi
Conventional automatic speech recognition (ASR) systems trained from frame-level alignments can easily leverage posterior fusion to improve ASR accuracy and build a better single m…
Language Modeling with Highway LSTM
Gakuto Kurata, Bhuvana Ramabhadran, George Saon +1
Language models (LMs) based on Long Short Term Memory (LSTM) have shown good gains in many automatic speech recognition tasks. In this paper, we extend an LSTM by adding highway ne…
English Conversational Telephone Speech Recognition by Humans and Machines
George Saon, Gakuto Kurata, Tom Sercu +9
One of the most difficult speech recognition tasks is accurate recognition of human to human communication. Advances in deep learning over the last few years have produced major sp…
Leveraging Sentence-level Information with Encoder LSTM for Semantic Slot Filling
Gakuto Kurata, Bing Xiang, Bowen Zhou +1
Recurrent Neural Network (RNN) and one of its specific architectures, Long Short-Term Memory (LSTM), have been widely used for sequence labeling. In this paper, we first enhance LS…