Related papers: Leveraging Redundancy in Multiple Audio Signals fo…

We present a new end-to-end architecture for automatic speech recognition (ASR) that can be trained using \emph{symbolic} input in addition to the traditional acoustic input. This architecture utilizes two separate encoders: one for…

This paper describes our RoyalFlush system for the track of multi-speaker automatic speech recognition (ASR) in the M2MeT challenge. We adopted the serialized output training (SOT) based multi-speakers ASR system with large-scale simulation…

Improving the efficiency of state-of-the-art methods in semantic segmentation requires overcoming the increasing computational cost as well as issues such as fusing semantic information from global and local contexts. Based on the recent…

This paper introduces a new method for multi-channel time domain speech separation in reverberant environments. A fully-convolutional neural network structure has been used to directly separate speech from multiple microphone recordings,…

Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the…

Acoustic echo cancellation (AEC) is an important speech signal processing technology that can remove echoes from microphone signals to enable natural-sounding full-duplex speech communication. While single-channel AEC is widely adopted,…

Recent advancements in scaling up models have significantly improved performance in Automatic Speech Recognition (ASR) tasks. However, training large ASR models from scratch remains costly. To address this issue, we introduce UME, a novel…

Automatic speech recognition in multi-channel reverberant conditions is a challenging task. The conventional way of suppressing the reverberation artifacts involves a beamforming based enhancement of the multi-channel speech signal, which…

Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…

In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously. The proposed framework is not only more compact but can also yield comparable…

Automatic speech recognition (ASR) systems typically use handcrafted feature extraction pipelines. To avoid their inherent information loss and to achieve more consistent modeling from speech to transcribed text, neural raw waveform feature…

Automatic speech recognition (ASR) systems often falter while processing stuttering-related disfluencies -- such as involuntary blocks and word repetitions -- yielding inaccurate transcripts. A critical barrier to progress is the scarcity…

We propose a novel method for generating scene-aware training data for far-field automatic speech recognition. We use a deep learning-based estimator to non-intrusively compute the sub-band reverberation time of an environment from its…

Due to the over-fitting problem caused by imbalance samples, there is still room to improve the performance of data-driven automatic modulation classification (AMC) in noisy scenarios. By fully considering the signal characteristics, an AMC…

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…

Estimating confidence scores for recognition results is a classic task in ASR field and of vital importance for kinds of downstream tasks and training strategies. Previous end-to-end~(E2E) based confidence estimation models (CEM) predict…

Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…

ASR remains unsatisfactory in scenarios where the speaking style diverges from that used to train ASR systems, resulting in erroneous transcripts. To address this, ASR Error Correction (AEC), a post-ASR processing approach, is required. In…

We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous…

Modern Automatic Speech Recognition (ASR) systems can achieve high performance in terms of recognition accuracy. However, a perfectly accurate transcript still can be challenging to read due to disfluency, filter words, and other errata…