相关论文: Multilingual Phonological Feature Recognition with…

We introduce polyglot language models, recurrent neural network models trained to predict symbol sequences in many different languages using shared representations of symbols and conditioning on typological information about the language to…

Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…

Multilingual spoken dialogue systems have gained prominence in the recent past necessitating the requirement for a front-end Language Identification (LID) system. Most of the existing LID systems rely on modeling the language discriminative…

In this paper we aim to automatically discover high quality frame-level speech features and acoustic tokens directly from unlabeled speech data. A Multi-granular Acoustic Tokenizer (MAT) was proposed for automatic discovery of multiple sets…

Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low…

Multichannel speech enhancement algorithms are essential for improving the intelligibility of speech signals in noisy environments. These algorithms are usually evaluated at the utterance level, but this approach overlooks the disparities…

This paper introduces a novel method to separate noisy speech into low or high frequency frames, in order to improve fundamental frequency (F0) estimation accuracy. In this proposal, the target signal is analyzed by means of the ensemble…

Wav2vec 2.0 (W2V2) has shown strong performance in pathological speech analysis by effectively capturing the characteristics of atypical speech. Despite its success, it remains unclear which components of its learned representations are…

The advancements of AI-synthesized human voices have introduced a growing threat of impersonation and disinformation. It is therefore of practical importance to developdetection methods for synthetic human voices. This work proposes a new…

Real-time speech enhancement (SE) is essential to online speech communication. Causal SE models use only the previous context while predicting future information, such as phoneme continuation, may help performing causal SE. The phonetic…

Graphemes of most languages encode pronunciation, though some are more explicit than others. Languages like Spanish have a straightforward mapping between its graphemes and phonemes, while this mapping is more convoluted for languages like…

There are different algorithms for vocal fold pathology diagnosis. These algorithms usually have three stages which are Feature Extraction, Feature Reduction and Classification. While the third stage implies a choice of a variety of machine…

In most current approaches of speech processing, information is extracted from the magnitude spectrum. However recent perceptual studies have underlined the importance of the phase component. The goal of this paper is to investigate the…

Phonetic error detection, a core subtask of automatic pronunciation assessment, identifies pronunciation deviations at the phoneme level. Speech variability from accents and dysfluencies challenges accurate phoneme recognition, with current…

Monaural speech enhancement has been widely studied using real networks in the time-frequency (TF) domain. However, the input and the target are naturally complex-valued in the TF domain, a fully complex network is highly desirable for…

In conversational speech, the acoustic signal provides cues that help listeners disambiguate difficult parses. For automatically parsing spoken utterances, we introduce a model that integrates transcribed text and acoustic-prosodic features…

In this paper, we present an improved model for voicing silent speech, where audio is synthesized from facial electromyography (EMG) signals. To give our model greater flexibility to learn its own input features, we directly use EMG signals…

The accuracy of automated speaker recognition is negatively impacted by change in emotions in a person's speech. In this paper, we hypothesize that speaker identity is composed of various vocal style factors that may be learned from…

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

Figures of speech help people express abstract concepts and evoke stronger emotions than literal expressions, thereby making texts more creative and engaging. Due to its pervasive and fundamental character, figurative language understanding…