相关论文: Robust Phonetic Segmentation Using Spectral Transi…

Mismatched transcriptions have been proposed as a mean to acquire probabilistic transcriptions from non-native speakers of a language.Prior work has demonstrated the value of these transcriptions by successfully adapting cross-lingual ASR…

Traditionally, the performance of non-native mispronunciation verification systems relied on effective phone-level labelling of non-native corpora. In this study, a multi-view approach is proposed to incorporate discriminative feature…

In this paper, we analyse the error patterns of the raw waveform acoustic models in TIMIT's phone recognition task. Our analysis goes beyond the conventional phone error rate (PER) metric. We categorise the phones into three groups:…

A major challenge in image segmentation is classifying object boundaries. Recent efforts propose to refine the segmentation result with boundary masks. However, models are still prone to misclassifying boundary pixels even when they…

In this paper, we propose a neural-based coding scheme in which an artificial neural network is exploited to automatically compress and decompress speech signals by a trainable approach. Having a two-stage training phase, the system can be…

Partial deepfake speech detection requires identifying manipulated regions that may occur within short temporal portions of an otherwise bona fide utterance, making the task particularly challenging for conventional utterance-level…

Connectionist temporal classification (CTC) provides an end-to-end acoustic model (AM) training strategy. CTC learns accurate AMs without time-aligned phonetic transcription, but sometimes fails to converge, especially in…

The goal of Audio-Visual Segmentation (AVS) is to localize and segment the sounding source objects from video frames. Research on AVS suffers from data scarcity due to the high cost of fine-grained manual annotations. Recent works attempt…

Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT)…

Existing Machine Translation (MT) research often suggests a single, fixed set of hyperparameters for word segmentation models, symmetric Byte Pair Encoding (BPE), which applies the same number of merge operations (NMO) to train tokenizers…

This work introduces sequential neural beamforming, which alternates between neural network based spectral separation and beamforming based spatial separation. Our neural networks for separation use an advanced convolutional architecture…

Existing speech enhancement methods mainly separate speech from noises at the signal level or in the time-frequency domain. They seldom pay attention to the semantic information of a corrupted signal. In this paper, we aim to bridge this…

Objective: Speech tests aim to estimate discrimination loss or speech recognition threshold (SRT). This paper investigates the potential to estimate SRTs from clinical data that target at characterizing the discrimination loss. Knowledge…

Phonetic segmentation is the process of splitting speech into distinct phonetic units. Human experts routinely perform this task manually by analyzing auditory and visual cues using analysis software, which is an extremely time-consuming…

This paper proposes a new pitch estimator and a novel pitch tracker for speakers. We first decompose the sound signal into subbands using an auditory filterbank, assuming time-frequency sparsity of human speech. Instead of directly…

In this work, a new Physics laboratory experiment on Acoustics beats is presented. We have designed a simple experimental setup to study superposition of sound waves of slightly different frequencies (acoustic beat). The microphone of a…

Recent works have introduced methods to estimate segmentation performance without ground truth, relying solely on neural network softmax outputs. These techniques hold potential for intuitive output quality control. However, such…

Spoken content, such as online videos and podcasts, often spans multiple topics, which makes automatic topic segmentation essential for user navigation and downstream applications. However, current methods do not fully leverage acoustic…

Learned speech representations can drastically improve performance on tasks with limited labeled data. However, due to their size and complexity, learned representations have limited utility in mobile settings where run-time performance can…

The end-to-end architecture has made promising progress in speech translation (ST). However, the ST task is still challenging under low-resource conditions. Most ST models have shown unsatisfactory results, especially in the absence of word…