Related papers: Two-Staged Acoustic Modeling Adaption for Robust S…
While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…
Automatic speech recognition systems have accomplished remarkable improvements in transcription accuracy in recent years. On some domains, models now achieve near-human performance. However, transcription performance on oral history has not…
High quality Automatic Speech Recognition (ASR) is a prerequisite for speech-based applications and research. While state-of-the-art ASR software is freely available, the language dependent acoustic models are lacking for languages other…
Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of…
In this work, we investigate application of generative speech enhancement to improve the robustness of ASR models in noisy and reverberant conditions. We employ a recently-proposed speech enhancement model based on Schr\"odinger bridge,…
Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually generated artificially, automatically finding errors in…
Compared with automatic speech recognition (ASR), the human auditory system is more adept at handling noise-adverse situations, including environmental noise and channel distortion. To mimic this adeptness, auditory models have been widely…
Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…
End-to-end models have achieved significant improvement on automatic speech recognition. One common method to improve performance of these models is expanding the data-space through data augmentation. Meanwhile, human auditory inspired…
The performance of automatic speech recognition systems degrades with increasing mismatch between the training and testing scenarios. Differences in speaker accents are a significant source of such mismatch. The traditional approach to deal…
Form about four decades human beings have been dreaming of an intelligent machine which can master the natural speech. In its simplest form, this machine should consist of two subsystems, namely automatic speech recognition (ASR) and speech…
Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…
Despite the significant progress made in the last years, state-of-the-art speech recognition technologies provide a satisfactory performance only in the close-talking condition. Robustness of distant speech recognition in adverse acoustic…
Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it…
This paper is concerned with automatic continuous speech recognition using trainable systems. The aim of this work is to build acoustic models for spoken Swedish. This is done employing hidden Markov models and using the SpeechDat database…
While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose…
Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set, an impractical scale for most researchers. In this work, we examine how linguistic and acoustic diversity in…
Speech impairments caused by conditions such as cerebral palsy or genetic disorders pose significant challenges for automatic speech recognition (ASR) systems. Despite recent advances, ASR models like Whisper struggle with non-normative…
Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…