Related papers: Speech2Phone: A Novel and Efficient Method for Tra…

Describes an audio dataset of spoken words designed to help train and evaluate keyword spotting systems. Discusses why this task is an interesting challenge, and why it requires a specialized dataset that is different from conventional…

Recent neural Text-to-Speech (TTS) models have been shown to perform very well when enough data is available. However, fine-tuning them for new speakers or languages is not straightforward in a low-resource setup. In this paper, we show…

While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…

The mechanism proposed here is for real-time speaker change detection in conversations, which firstly trains a neural network text-independent speaker classifier using in-domain speaker data. Through the network, features of conversational…

With 4.5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition. We propose data selection techniques to…

The ResNet-based architecture has been widely adopted to extract speaker embeddings for text-independent speaker verification systems. By introducing the residual connections to the CNN and standardizing the residual blocks, the ResNet…

This paper describes a novel method of live keyword spotting using a two-stage time delay neural network. The model is trained using transfer learning: initial training with phone targets from a large speech corpus is followed by training…

The task of grapheme-to-phoneme (G2P) conversion is important for both speech recognition and synthesis. Similar to other speech and language processing tasks, in a scenario where only small-sized training data are available, learning G2P…

In this work we evaluate the utility of synthetic data for training automatic speech recognition (ASR). We use the ASR training data to train a text-to-speech (TTS) system similar to FastSpeech-2. With this TTS we reproduce the original…

The emergence of industrial-scale speech recognition (ASR) models such as Whisper and USM, trained on 1M hours of weakly labelled and 12M hours of audio only proprietary data respectively, has led to a stronger need for large scale public…

Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in…

To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the…

Speech-to-speech translation (S2ST) converts input speech to speech in another language. A challenge of delivering S2ST in real time is the accumulated delay between the translation and speech synthesis modules. While recently incremental…

Training the state-of-the-art speech-to-text (STT) models in mobile devices is challenging due to its limited resources relative to a server environment. In addition, these models are trained on generic datasets that are not exhaustive in…

In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…

Speech-to-text translation has many potential applications for low-resource languages, but the typical approach of cascading speech recognition with machine translation is often impossible, since the transcripts needed to train a speech…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…

Current state of the art acoustic models can easily comprise more than 100 million parameters. This growing complexity demands larger training datasets to maintain a decent generalization of the final decision function. An ideal dataset is…

Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in…