Related papers: WhisperRT -- Turning Whisper into a Causal Streami…

Recently, attention-based encoder-decoder (AED) end-to-end (E2E) models have drawn more and more attention in the field of automatic speech recognition (ASR). AED models, however, still have drawbacks when deploying in commercial…

Simultaneous speech-to-text translation is widely useful in many scenarios. The conventional cascaded approach uses a pipeline of streaming ASR followed by simultaneous MT, but suffers from error propagation and extra latency. To alleviate…

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.…

Audio-native large language models (audio-LLMs) commonly use Whisper as their audio encoder. However, Whisper was trained exclusively on speech data, producing weak representations for music and environmental sound. This forces downstream…

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…

In this paper, we explore the untapped potential of Whisper, a well-established automatic speech recognition (ASR) foundation model, in the context of L2 spoken language assessment (SLA). Unlike prior studies that extrinsically analyze…

This paper improves the streaming transformer transducer for speech recognition by using non-causal convolution. Many works apply the causal convolution to improve streaming transformer ignoring the lookahead context. We propose to use…

We propose DarkStream, a streaming speech synthesis model for real-time speaker anonymization. To improve content encoding under strict latency constraints, DarkStream combines a causal waveform encoder, a short lookahead buffer, and…

Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings. There has been far less work, however, on the zero-shot…

Transducer is one of the mainstream frameworks for streaming speech recognition. There is a performance gap between the streaming and non-streaming transducer models due to limited context. To reduce this gap, an effective way is to ensure…

Automatic Speech Recognition (ASR) in conversational settings presents unique challenges, including extracting relevant contextual information from previous conversational turns. Due to irrelevant content, error propagation, and redundancy,…

The Transformer-based Whisper model has achieved state-of-the-art performance in Automatic Speech Recognition (ASR). However, its Multi-Head Attention (MHA) mechanism results in significant GPU memory consumption due to the linearly growing…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Voice-enabled commercial products are ubiquitous, typically enabled by lightweight on-device keyword spotting (KWS) and full automatic speech recognition (ASR) in the cloud. ASR systems require significant computational resources in…

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…

Automatic speech recognition (ASR) systems are primarily evaluated on transcription accuracy. However, in some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time.…

The attention-based Transformer model has achieved promising results for speech recognition (SR) in the offline mode. However, in the streaming mode, the Transformer model usually incurs significant latency to maintain its recognition…

On-device end-to-end (E2E) models have shown improvements over a conventional model on English Voice Search tasks in both quality and latency. E2E models have also shown promising results for multilingual automatic speech recognition (ASR).…

Streaming Automatic Speech Recognition (ASR) in voice assistants can utilize prefetching to partially hide the latency of response generation. Prefetching involves passing a preliminary ASR hypothesis to downstream systems in order to…

Discretized representations of speech signals are efficient alternatives to continuous features for various speech applications, including automatic speech recognition (ASR) and speech language models. However, these representations, such…