相关论文: Beyond the Utterance: An Empirical Study of Very L…

Modern neural speech models benefit from having longer context, and many approaches have been proposed to increase the maximum context a model can use. However, few have attempted to measure how much context these models actually use, i.e.,…

To build an automatic speech recognition (ASR) system that can serve everyone in the world, the ASR needs to be robust to a wide range of accents including unseen accents. We systematically study how three different variables in training…

Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint…

In this paper, we analyzed how audio-visual speech enhancement can help to perform the ASR task in a cocktail party scenario. Therefore we considered two simple end-to-end LSTM-based models that perform single-channel audio-visual speech…

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

General-purpose automatic speech recognition (ASR) systems do not always perform well in goal-oriented dialogue. Existing ASR correction methods rely on prior user data or named entities. We extend correction to tasks that have no prior…

Automatic Speech Recognition (ASR) is an active field of research due to its large number of applications and the proliferation of interfaces or computing devices that can support speech processing. However, the bulk of applications are…

Building competitive automatic speech recognition (ASR) models usually requires large-scale au- dio supervision, which makes reproduction and specialization expensive. We study Ark-ASR, a 0.6B- parameter audio-conditioned language model…

Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of parameters, leading to slow inferences even with adapted hardware. In this context,…

Automatic speech recognition (ASR) systems play a key role in many commercial products including voice assistants. Typically, they require large amounts of clean speech data for training which gives an undue advantage to large organizations…

Speaker recognition performance has been greatly improved with the emergence of deep learning. Deep neural networks show the capacity to effectively deal with impacts of noise and reverberation, making them attractive to far-field speaker…

This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR…

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of…

Self-attention has become an important and widely used neural network component that helped to establish new state-of-the-art results for various applications, such as machine translation and automatic speech recognition (ASR). However, the…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

In most automatic speech recognition (ASR) systems, the audio signal is processed to produce a time series of sensor measurements (e.g., filterbank outputs). This time series encodes semantic information in a speaker-dependent way. An…

End-to-end automatic speech recognition (ASR), unlike conventional ASR, does not have modules to learn the semantic representation from speech encoder. Moreover, the higher frame-rate of speech representation prevents the model to learn the…

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In…