Related papers: Spatial Processing Front-End For Distant ASR Explo…

Transformer models have been introduced into end-to-end speech recognition with state-of-the-art performance on various tasks owing to their superiority in modeling long-term dependencies. However, such improvements are usually obtained…

Conventional automatic speech recognition (ASR) models typically produce outputs as normalized texts lacking punctuation and capitalization, necessitating post-processing models to enhance readability. This approach, however, introduces…

Recently, deep convolutional neural networks (CNNs) have obtained promising results in image processing tasks including super-resolution (SR). However, most CNN-based SR methods treat low-resolution (LR) inputs and features equally across…

In recent years, the evolution of end-to-end (E2E) automatic speech recognition (ASR) models has been remarkable, largely due to advances in deep learning architectures like transformer. On top of E2E systems, researchers have achieved…

Speech-to-text errors made by automatic speech recognition (ASR) systems negatively impact downstream models. Error correction models as a post-processing text editing method have been recently developed for refining the ASR outputs.…

Speech separation in realistic acoustic environments remains challenging because overlapping speakers, background noise, and reverberation must be resolved simultaneously. Although recent time-frequency (TF) domain models have shown strong…

Target speech extraction (TSE) systems are designed to extract target speech from a multi-talker mixture. The popular training objective for most prior TSE networks is to enhance reconstruction performance of extracted speech waveform.…

Existing speaker diarization systems typically rely on large amounts of manually annotated data, which is labor-intensive and difficult to obtain, especially in real-world scenarios. Additionally, language-specific constraints in these…

Speech dereverberation aims to alleviate the detrimental effects of late-reverberant components. While the weighted prediction error (WPE) method has shown superior performance in dereverberation, there is still room for further improvement…

Acoustic word embeddings (AWEs) are vector representations of spoken words. An effective method for obtaining AWEs is the Correspondence Auto-Encoder (CAE). In the past, the CAE method has been associated with traditional MFCC features.…

In large scale dynamic wireless networks, the amount of overhead caused by channel estimation (CE) is becoming one of the main performance bottlenecks. This is due to the large number users whose channels should be estimated, the user…

Existing speech emotion recognition (SER) methods commonly suffer from the lack of high-quality large-scale corpus, partly due to the complex, psychological nature of emotion which makes accurate labeling difficult and time consuming.…

Recent progress in learning-based image compression has demonstrated that end-to-end optimization can substantially outperform traditional codecs by jointly learning compact latent representations and probabilistic entropy models. However,…

Multi-speaker speech recognition has been one of the keychallenges in conversation transcription as it breaks the singleactive speaker assumption employed by most state-of-the-artspeech recognition systems. Speech separation is consideredas…

The mismatch of speech length and text length poses a challenge in automatic speech recognition (ASR). In previous research, various approaches have been employed to align text with speech, including the utilization of Connectionist…

Historically lower-level tasks such as automatic speech recognition (ASR) and speaker identification are the main focus in the speech field. Interest has been growing in higher-level spoken language understanding (SLU) tasks recently, like…

A stream attention framework has been applied to the posterior probabilities of the deep neural network (DNN) to improve the far-field automatic speech recognition (ASR) performance in the multi-microphone configuration. The stream…

End-to-end automatic speech recognition (ASR) models often struggle to accurately recognize rare words. Previously, we introduced an ASR postprocessing method called error detection and context-aware error correction (ED-CEC), which…

Discriminatory channel estimation (DCE) is a recently developed strategy to enlarge the performance difference between a legitimate receiver (LR) and an unauthorized receiver (UR) in a multiple-input multiple-output (MIMO) wireless system.…

This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the…