Related papers: Detection of Prosodic Boundaries in Speech Using W…

Collecting everyday speech data for prosodic analysis is challenging due to the confounding of prosody and semantics, privacy constraints, and participant compliance. We introduce and empirically evaluate a content-controlled, privacy-first…

Modern Arabic ASR systems such as wav2vec 2.0 excel at word- and sentence-level transcription, yet struggle to classify isolated letters. In this study, we show that this phoneme-level task, crucial for language learning, speech therapy,…

Detection of transitions between broad phonetic classes in a speech signal is an important problem which has applications such as landmark detection and segmentation. The proposed hierarchical method detects silence to non-silence…

An experimental approach to studying the properties of word embeddings is proposed. Controlled experiments, achieved through modifications of the training corpus, permit the demonstration of direct relations between word properties and word…

MOS (Mean Opinion Score) is a subjective method used for the evaluation of a system's quality. Telecommunications (for voice and video), and speech synthesis systems (for generated speech) are a few of the many applications of the method.…

Self-supervised models, namely, wav2vec and its variants, have shown promising results in various downstream tasks in the speech domain. However, their inner workings are poorly understood, calling for in-depth analyses on what the model…

Direct acoustics-to-word (A2W) systems for end-to-end automatic speech recognition are simpler to train, and more efficient to decode with, than sub-word systems. However, A2W systems can have difficulties at training time when data is…

Whispering is an important mode of human speech, but no end-to-end recognition results for it were reported yet, probably due to the scarcity of available whispered speech data. In this paper, we present several approaches for end-to-end…

Speaker verification (SV) performance deteriorates as utterances become shorter. To this end, we propose a new architecture called VoiceExtender which provides a promising solution for improving SV performance when handling short-duration…

We present Burst2Vec, our multi-task learning approach to predict emotion, age, and origin (i.e., native country/language) from vocal bursts. Burst2Vec utilises pre-trained speech representations to capture acoustic information from raw…

Spoken language diarization (LD) and related tasks are mostly explored using the phonotactic approach. Phonotactic approaches mostly use explicit way of language modeling, hence requiring intermediate phoneme modeling and transcribed data.…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Large-scale auto-regressive language models pretrained on massive text have demonstrated their impressive ability to perform new natural language tasks with only a few text examples, without the need for fine-tuning. Recent studies further…

Automatic Speech Recognition (ASR) systems have progressed significantly in their performance on adult speech data; however, transcribing child speech remains challenging due to the acoustic differences in the characteristics of child and…

Child literacy is a strong predictor of life outcomes at the subsequent stages of an individual's life. This points to a need for targeted interventions in vulnerable low and middle income populations to help bridge the gap between literacy…

In this paper, we present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech, and subsequently fine-tuning the model on automatic speech…

Prosodic cues in conversational speech aid listeners in discerning a message. We investigate whether acoustic cues in spoken dialogue can be used to identify the importance of individual words to the meaning of a conversation turn.…

This paper explores predicting suitable prosodic features for fine-grained emotion analysis from the discourse-level text. To obtain fine-grained emotional prosodic features as predictive values for our model, we extract a phoneme-level…

Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. However, variational autoencoders are trained on clean speech only, which…

Many applications of speech communication and speaker identification suffer from the problem of co-channel speech. This paper deals with a multi-resolution dyadic wavelet transform method for usable segments of co-channel speech detection…