Related papers: M2H-GAN: A GAN-based Mapping from Machine to Human…

Speech Emotion Recognition (SER) task has known significant improvements over the last years with the advent of Deep Neural Networks (DNNs). However, even the most successful methods are still rather failing when adaptation to specific…

Spoken Language Understanding (SLU) is the problem of extracting the meaning from speech utterances. It is typically addressed as a two-step problem, where an Automatic Speech Recognition (ASR) model is employed to convert speech into text,…

Deep neural networks (DNNs) have been demonstrated to outperform many traditional machine learning algorithms in Automatic Speech Recognition (ASR). In this paper, we show that a large improvement in the accuracy of deep speech models can…

Much recent work on Spoken Language Understanding (SLU) falls short in at least one of three ways: models were trained on oracle text input and neglected the Automatics Speech Recognition (ASR) outputs, models were trained to predict only…

It is important to transcribe and archive speech data of endangered languages for preserving heritages of verbal culture and automatic speech recognition (ASR) is a powerful tool to facilitate this process. However, since endangered…

Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…

Deep learning models trained in a supervised setting have revolutionized audio and speech processing. However, their performance inherently depends on the quantity of human-annotated data, making them costly to scale and prone to poor…

Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence…

In realistic environments, speech is usually interfered by various noise and reverberation, which dramatically degrades the performance of automatic speech recognition (ASR) systems. To alleviate this issue, the commonest way is to use a…

One way to interpret trained deep neural networks (DNNs) is by inspecting characteristics that neurons in the model respond to, such as by iteratively optimising the model input (e.g., an image) to maximally activate specific neurons.…

This paper addresses the problem of automatic speech recognition (ASR) error detection and their use for improving spoken language understanding (SLU) systems. In this study, the SLU task consists in automatically extracting, from ASR…

The combination of a deep neural network (DNN) -based speech enhancement (SE) front-end and an automatic speech recognition (ASR) back-end is a widely used approach to implement overlapping speech recognition. However, the SE front-end…

Hashing has been a widely-adopted technique for nearest neighbor search in large-scale image retrieval tasks. Recent research has shown that leveraging supervised information can lead to high quality hashing. However, the cost of annotating…

Conventional time-delay neural networks (TDNNs) struggle to handle long-range context, their ability to represent speaker information is therefore limited in long utterances. Existing solutions either depend on increasing model complexity…

This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations". Similar to the previous year's…

The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due to the noise, etc. In this case, the acoustic information can be less reliable.…

Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…

Addressing the detrimental impact of non-stationary environmental noise on automatic speech recognition (ASR) has been a persistent and significant research focus. Despite advancements, this challenge continues to be a major concern.…

A deep neural network (DNN)-based speech enhancement (SE) aiming to maximize the performance of an automatic speech recognition (ASR) system is proposed in this paper. In order to optimize the DNN-based SE model in terms of the character…

Deep-neural-network (DNN) based noise suppression systems yield significant improvements over conventional approaches such as spectral subtraction and non-negative matrix factorization, but do not generalize well to noise conditions they…