14 accepted papers
There is an on-going body of research on training separate dedicated models for either short-form or long-form utterances. Multi-form acoustic models that are simply trained on combined data from long-form and short-form utterances often suffer from various negative impacts due to the diversity of a…
Limited transcribed spoken style data is a critical bottleneck in building automatic speech recognition (ASR) systems for low-resource languages. Prompting a large language model (LLM) to paraphrase input text can generate novel text data that is constrained to be semantically similar to the source…
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. However, existing works only transfer a single representation of LLM (e.g. the last layer of pretrained BERT), while the…
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 for EC are collected by automatically pairing a large set of ASR hypotheses (as sources) and their gold references (as targ…
Despite the impressive performance of ASR models on mainstream benchmarks, their performance on rare words is unsatisfactory. In enterprise settings, often a focused list of entities (such as locations, names, etc) are available which can be used to adapt the model to the terminology of specific dom…
This paper proposes an improved generalized knowledge distillation framework with multiple dissimilar teacher networks, each of which is specialized for a specific domain, to make a deployable student network more robust to challenging acoustic environments. In this paper, we first address a method…
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 three practical settings: a case where verbatim transcripts are available, a constrained case where the only available ann…
When building a language model (LM) for spontaneous speech, the ideal situation is to have a large amount of spoken, in-domain training data. Having such abundant data, however, is not realistic. We address this problem by generating texts in spoken language from those in written language by using a…
We present our work on training speaker embeddings, especially effective for speaker diarization. For various speaker recognition tasks, extracting speaker embeddings using Deep Neural Networks (DNNs) has become major methods. These embeddings are generally trained to be discriminate speakers and be…
With recent advances in deep learning, considerable attention has been given to achieving automatic speech recognition performance close to human performance on tasks like conversational telephone speech (CTS) recognition. In this paper we evaluate the usefulness of these proposed techniques on broa…
Although neural language models have emerged, n-gram language models are still used for many speech recognition tasks. This paper proposes four methods to improve n-gram language models using text generated from a recurrent neural network language model (RNNLM). First, we use multiple RNNLMs from di…
Neural Network (NN) based acoustic frontends, such as denoising autoencoders, are actively being investigated to improve the robustness of NN based acoustic models to various noise conditions. In recent work the joint training of such frontends with backend NNs has been shown to significantly improv…
Acoustic modeling with deep learning has drastically improved the performance of automatic speech recognition (ASR) where the main stream of the acoustic feature is still log-Mel filtered one. While the log-Mel filtered features lose harmonic-structure information, they still include useful informat…
Monaural (single-channel) recording is sometimes used for telephone conversations in call centers. Generally speaking, the accuracy of automatic speech recognition of a monaural recording is worse than that of the multi-channel recording of the same conversation where each speaker's voice is separat…