Related papers: Reducing the gap between streaming and non-streami…

Leveraging knowledge from multiple tasks through introducing a small number of task specific parameters into each transformer layer, also known as adapters, receives much attention recently. However, adding an extra fusion layer to…

Voice technology has become ubiquitous recently. However, the accuracy, and hence experience, in different languages varies significantly, which makes the technology not equally inclusive. The availability of data for different languages is…

End-to-end intent classification using speech has numerous advantages compared to the conventional pipeline approach using automatic speech recognition (ASR), followed by natural language processing modules. It attempts to predict intent…

The remarkable performance of the pre-trained language model (LM) using self-supervised learning has led to a major paradigm shift in the study of natural language processing. In line with these changes, leveraging the performance of speech…

The Streaming Unmixing and Recognition Transducer (SURT) model was proposed recently as an end-to-end approach for continuous, streaming, multi-talker speech recognition (ASR). Despite impressive results on multi-turn meetings, SURT has…

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

Knowledge distillation has been widely used to compress existing deep learning models while preserving the performance on a wide range of applications. In the specific context of Automatic Speech Recognition (ASR), distillation from…

Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited…

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

In real-world applications, users often require both translations and transcriptions of speech to enhance their comprehension, particularly in streaming scenarios where incremental generation is necessary. This paper introduces a streaming…

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

This paper explores the use of ASR-pretrained Conformers for speaker verification, leveraging their strengths in modeling speech signals. We introduce three strategies: (1) Transfer learning to initialize the speaker embedding network,…

Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience.…

Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…

A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.…

We propose a simple yet effective method to compress an RNN-Transducer (RNN-T) through the well-known knowledge distillation paradigm. We show that the transducer's encoder outputs naturally have a high entropy and contain rich information…

Although end-to-end (E2E) automatic speech recognition (ASR) has shown state-of-the-art recognition accuracy, it tends to be implicitly biased towards the training data distribution which can degrade generalisation. This paper proposes a…