相关论文: Autosegmental Neural Nets: Should Phones and Tones…

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…

Self-supervised representations of speech are currently being widely used for a large number of applications. Recently, some efforts have been made in trying to analyze the type of information present in each of these representations. Most…

How much audio is needed to fully observe a multilingual ASR model's learned sub-token inventory across languages, and does data disparity in multilingual pre-training affect how these tokens are utilized during inference? We address this…

This paper is devoted to improve automatic emotion recognition from speech by incorporating rhythm and temporal features. Research on automatic emotion recognition so far has mostly been based on applying features like MFCCs, pitch and…

Ultrasound tongue imaging is used to visualise the intra-oral articulators during speech production. It is utilised in a range of applications, including speech and language therapy and phonetics research. Ultrasound and speech audio are…

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…

Speech models have gained traction thanks to increase in accuracy from novel transformer architectures. While this impressive increase in performance across automatic speech recognition (ASR) benchmarks is noteworthy, there is still much…

In this paper, we present a unified model that works for both multilingual and crosslingual prediction of reading times of words in various languages. The secret behind the success of this model is in the preprocessing step where all words…

Speech separation remains an important topic for multi-speaker technology researchers. Convolution augmented transformers (conformers) have performed well for many speech processing tasks but have been under-researched for speech…

Automatic pronunciation assessment (APA) analyzes second-language (L2) learners' speech by providing fine-grained pronunciation feedback at various linguistic levels. Most existing efforts on APA typically adopt segmental-level features as…

Interpretability research has shown that self-supervised Spoken Language Models (SLMs) encode a wide variety of features in human speech from the acoustic, phonetic, phonological, syntactic and semantic levels, to speaker characteristics.…

The speech signal is a consummate example of time-series data. The acoustics of the signal change over time, sometimes dramatically. Yet, the most common type of comparison we perform in phonetics is between instantaneous acoustic…

We investigate the performance on phoneme categorization and phoneme and word segmentation of several self-supervised learning (SSL) methods based on Contrastive Predictive Coding (CPC). Our experiments show that with the existing…

In this paper, we study the disentanglement of speaker and language representations in non-autoregressive cross-lingual TTS models from various aspects. We propose a phoneme length regulator that solves the length mismatch problem between…

Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target…

For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a…

Recent years have witnessed significant improvement in ASR systems to recognize spoken utterances. However, it is still a challenging task for noisy and out-of-domain data, where substitution and deletion errors are prevalent in the…

Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the…

Modern automatic speech recognition (ASR) systems have been observed to function better for certain speaker groups (SGs) than others, despite recent gains in overall performance. One potential impediment to progress towards fairer ASR is a…

Through proliferation on smartphones and smart speakers, intelligent personal assistants (IPAs) have made speech a common interaction modality. Yet, due to linguistic coverage and varying levels of functionality, many speakers engage with…