Related papers: Punctuation Prediction Model for Conversational Sp…

Conversational speech normally is embodied with loose syntactic structures at the utterance level but simultaneously exhibits topical coherence relations across consecutive utterances. Prior work has shown that capturing longer context…

When applying automated speech recognition (ASR) for Belgian Dutch (Van Dyck et al. 2021), the output consists of an unsegmented stream of words, without any punctuation. A next step is to perform segmentation and insert punctuation, making…

Joint punctuated and normalized automatic speech recognition (ASR) aims at outputing transcripts with and without punctuation and casing. This task remains challenging due to the lack of paired speech and punctuated text data in most ASR…

While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation problems, resulting…

Pause insertion, also known as phrase break prediction and phrasing, is an essential part of TTS systems because proper pauses with natural duration significantly enhance the rhythm and intelligibility of synthetic speech. However,…

Automatic classification of disordered speech can provide an objective tool for identifying the presence and severity of speech impairment. Classification approaches can also help identify hard-to-recognize speech samples to teach ASR…

Recent works using artificial neural networks based on word distributed representation greatly boost the performance of various natural language learning tasks, especially question answering. Though, they also carry along with some…

Alzheimer's Disease (AD) is the world's leading neurodegenerative disease, which often results in communication difficulties. Analysing speech can serve as a diagnostic tool for identifying the condition. The recent ADReSS challenge…

Traditional automatic speech recognition (ASR) models output lower-cased words without punctuation marks, which reduces readability and necessitates a subsequent text processing model to convert ASR transcripts into a proper format.…

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase or partial…

Speech production is a complex sequential process which involve the coordination of various articulatory features. Among them tongue being a highly versatile active articulator responsible for shaping airflow to produce targeted speech…

Since Bahdanau et al. [1] first introduced attention for neural machine translation, most sequence-to-sequence models made use of attention mechanisms [2, 3, 4]. While they produce soft-alignment matrices that could be interpreted as…

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…

We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition. More recently, we have shown that the performance…

Punctuation is critical in understanding natural language text. Currently, most automatic speech recognition (ASR) systems do not generate punctuation, which affects the performance of downstream tasks, such as intent detection and slot…

Speech disfluency commonly occurs in conversational and spontaneous speech. However, standard Automatic Speech Recognition (ASR) models struggle to accurately recognize these disfluencies because they are typically trained on fluent…

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in…

We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up…

Recently, Convolutional Neural Network (CNN) and Long short-term memory (LSTM) based models have been introduced to deep learning-based target speaker separation. In this paper, we propose an Attention-based neural network (Atss-Net) in the…

We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable…