Sorry, you need to enable JavaScript to visit this website.

Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but also navigate the intricacies of linguistic diversity. In this paper, we address the aforementioned ASR challenge, focusing on the Tunisian dialect. First, textual and audio data is collected and in some cases annotated.

Automated audio captioning (AAC) aims to generate informative descriptions for various sounds from nature and/or human activities. In recent years, AAC has quickly attracted research interest, with state-of-the-art systems now relying on a sequence-to-sequence (seq2seq) backbone powered by strong models such as Transformers. Following the macro-trend of applied machine learning research, in this work, we strive to improve the performance of seq2seq AAC models by extensively leveraging pretrained models and large language models (LLMs).

Inthis paper,we present a sound field interpolation for array signal processing (ASP) that is robust to rotation of a circular microphone array (CMA), and we evaluate beamforming as one of its applications. Most ASP methods assume a time-invariantacoustic transfer system (ATS) from sources to the microphone array. This assumption makes it challenging to perform ASP in real situations where sources and the microphone array can move. Therefore, considering a time-variant ATS is an essential task for the use of ASP.

Phase gradients can help enforce phase consistency across time and frequency, further improving the output of speech enhancement approaches. Recently, neural networks were used to estimate the phase gradients from the short-term amplitude spectra of clean speech. These were then used to synthesise phase to reconstruct a plausible time-domain signal. However, using purely synthetic phase in speech enhancement yields unnatural-sounding output. Therefore we derive a closed-form phase estimate that combines the synthetic phase with that of the enhanced speech, yielding more natural output.

ICASSP2024 poster

Previous Multimodal Information based Speech Processing (MISP) challenges mainly focused on audio-visual speech recognition (AVSR) with commendable success. However, the most advanced back-end recognition systems often hit performance limits due to the complex acoustic environments. This has prompted a shift in focus towards the Audio-Visual Target Speaker Extraction (AVTSE) task for the MISP 2023 challenge in ICASSP 2024 Signal Processing Grand Challenges.

Predicting mental health conditions from speech has been widely explored in recent years. Most studies rely on a single sample from each subject to detect indicators of a particular disorder. These studies ignore two important facts: certain mental disorders tend to co-exist, and their severity tends to vary over time.

Perceptual evaluation constitutes a crucial aspect of various audio-processing tasks. Full reference (FR) or similarity-based metrics rely on high-quality reference recordings, to which lower-quality or corrupted versions of the recording may be compared for evaluation. In contrast, no-reference (NR) metrics evaluate a recording without relying on a reference. Both the FR and NR approaches exhibit advantages and drawbacks relative to each other.

Recently, vulnerable samples have been shown to be crucial
for improving adversarial training performance. Our analysis
on existing vulnerable samples mining methods indicate that
existing methods have two problems: 1) valuable connections
among different pairs of natural samples and their adversarial
counterparts are ignored; 2) parts of vulnerable samples are
unconsidered. To better leverage vulnerable samples, we propose INter PAir ConstrainT (INPACT) and Vulnerable Aware

This paper presents a detailed description of our proposed methods for the ICASSP 2024 Cadenza Challenge. Experimental results show that the proposed system can achieve better performance than official baselines.