Suyoun Kim


2023

pdf
Introducing Semantics into Speech Encoders
Derek Xu | Shuyan Dong | Changhan Wang | Suyoun Kim | Zhaojiang Lin | Bing Liu | Akshat Shrivastava | Shang-Wen Li | Liang-Hsuan Tseng | Guan-Ting Lin | Alexei Baevski | Hung-yi Lee | Yizhou Sun | Wei Wang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Recent studies find existing self-supervised speech encoders contain primarily acoustic rather than semantic information. As a result, pipelined supervised automatic speech recognition (ASR) to large language model (LLM) systems achieve state-of-the-art results on semantic spoken language tasks by utilizing rich semantic representations from the LLM. These systems come at the cost of labeled audio transcriptions, which is expensive and time-consuming to obtain. We propose a task-agnostic unsupervised way of incorporating semantic information from LLMs into self-supervised speech encoders without labeled audio transcriptions. By introducing semantics, we improve existing speech encoder spoken language understanding (SLU) performance by over 5% on intent classification (IC), with modest gains in named entity resolution (NER) and slot filling (SF), and spoken question answering (SQA) FF1 score by over 2%. Our approach, which uses no ASR data, achieves similar performance as methods trained on over 100 hours of labeled audio transcripts, demonstrating the feasibility of unsupervised semantic augmentations to existing speech encoders.

2022

pdf
Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition
Suyoun Kim | Ke Li | Lucas Kabela | Ron Huang | Jiedan Zhu | Ozlem Kalinli | Duc Le
Findings of the Association for Computational Linguistics: EMNLP 2022

Recently, there has been an increasing interest in two-pass streaming end-to-end speech recognition (ASR) that incorporates a 2nd-pass rescoring model on top of the conventional 1st-pass streaming ASR model to improve recognition accuracy while keeping latency low. One of the latest 2nd-pass rescoring model, Transformer Rescorer, takes the n-best initial outputs and audio embeddings from the 1st-pass model, and then choose the best output by re-scoring the n-best initial outputs. However, training this Transformer Rescorer requires expensive paired audio-text training data because the model uses audio embeddings as input. In this work, we present our Joint Audio/Text training method for Transformer Rescorer, to leverage unpaired text-only data which is relatively cheaper than paired audio-text data. We evaluate Transformer Rescorer with our Joint Audio/Text training on Librispeech dataset as well as our large-scale in-house dataset and show that our training method can improve word error rate (WER) significantly compared to standard Transformer Rescorer without requiring any extra model parameters or latency.

2019

pdf
Acoustic-to-Word Models with Conversational Context Information
Suyoun Kim | Florian Metze
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Conversational context information, higher-level knowledge that spans across sentences, can help to recognize a long conversation. However, existing speech recognition models are typically built at a sentence level, and thus it may not capture important conversational context information. The recent progress in end-to-end speech recognition enables integrating context with other available information (e.g., acoustic, linguistic resources) and directly recognizing words from speech. In this work, we present a direct acoustic-to-word, end-to-end speech recognition model capable of utilizing the conversational context to better process long conversations. We evaluate our proposed approach on the Switchboard conversational speech corpus and show that our system outperforms a standard end-to-end speech recognition system.

pdf
Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion
Suyoun Kim | Siddharth Dalmia | Florian Metze
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We present a novel conversational-context aware end-to-end speech recognizer based on a gated neural network that incorporates conversational-context/word/speech embeddings. Unlike conventional speech recognition models, our model learns longer conversational-context information that spans across sentences and is consequently better at recognizing long conversations. Specifically, we propose to use text-based external word and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end framework, yielding significant improvement in word error rate with better conversational-context representation. We evaluated the models on the Switchboard conversational speech corpus and show that our model outperforms standard end-to-end speech recognition models.