2 citations · 4 across the 7 of their papers we have counts for
7 papers
Conversational Speech Naturalness Predictor
Anfeng Xu, Yashesh Gaur, Naoyuki Kanda +6
Evaluation of conversational naturalness is essential for developing human-like speech agents. However, existing speech naturalness predictors are often designed to assess utteranc…
Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
Keqi Deng, Jinxi Guo, Yingyi Ma +4
While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel…
Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning
Yingyi Ma, Zhe Liu, Ozlem Kalinli
The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-…
Correction Focused Language Model Training for Speech Recognition
Yingyi Ma, Zhe Liu, Ozlem Kalinli
Language models (LMs) have been commonly adopted to boost the performance of automatic speech recognition (ASR) particularly in domain adaptation tasks. Conventional way of LM trai…
Forgetting Private Textual Sequences in Language Models via Leave-One-Out Ensemble
Zhe Liu, Ozlem Kalinli
Recent research has shown that language models have a tendency to memorize rare or unique token sequences in the training corpus. After deploying a model, practitioners might be as…
Contextual Biasing of Named-Entities with Large Language Models
Chuanneng Sun, Zeeshan Ahmed, Yingyi Ma +4
This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automati…
Recovering from Privacy-Preserving Masking with Large Language Models
Arpita Vats, Zhe Liu, Peng Su +5
Model adaptation is crucial to handle the discrepancy between proxy training data and actual users data received. To effectively perform adaptation, textual data of users is typica…