Speech and Language Processing

The ICASSP 2023 Speech Signal Improvement Challenge is intended to stimulate research in the area of improving the speech signal quality in communication systems. The speech signal quality can be measured with SIG in ITU-T P.835 and is still a top issue in audio communication and conferencing systems. For example, in the ICASSP 2022 Deep Noise Suppression challenge, the improvement in the background (BAK) and overall (OVRL) quality is impressive, but the improvement in the speech signal (SIG) is statistically zero.

The LIMMITS’23 challenge on LIghtweight, Multi-speaker, Multi-lingual Indic Text-to-Speech Synthesis is being organized as part of the Signal Processing Grand Challenge track at ICASSP 2023. As a part of this challenge, TTS corpora in Marathi, Hindi, and Telugu datasets will be released. These TTS corpora are being built in the SYSPIN project at SPIRE lab, Indian Institute of Science (IISc) Bangalore, India.

The advent of spoken language processing (SLP) technologies on meeting transcripts is crucial for distilling, organizing, and prioritizing information. Meeting transcripts impose two key challenges to SLP tasks.  First, meeting transcripts exhibit a wide variety of spoken language phenomena, leading to dramatic performance degradation.  Second, meeting transcripts are usually long-form documents with several thousand words or more, posing a great challenge to mainstay Transformer-based models with high computational complexity.

The MADReSS SPGC targets a difficult automatic prediction problem of societal and medical relevance, namely, the detection of Alzheimer’s Dementia (AD). Dementia is a category of neurodegenerative diseases that entails a long-term and usually gradual decrease of cognitive functioning.

Spoken Language Understanding (SLU) is a critical component of conversational voice assistants, requiring converting user utterances into a structured format for task executions. SLU systems typically consist of an ASR component to convert audio to text and an NLU component to convert text to a tree like structure, however recently, E2E SLU systems have also become of increasing interest in order to increase quality, model efficiency, and data efficiency.

This signal processing challenge is designed to get the latest advancements in speech enhancement applied to hearing aids. 430 million people worldwide require rehabilitation to address hearing loss. Yet even in developed countries, only 40% of people who could benefit from hearing aids have them and use them often enough, because they believe that hearing aids perform poorly.

The Multimodal Information Based Speech Processing (MISP) 2022 Challenge aims to extend the application of signal processing technology in specific scenarios, using audio and video data. We target the home TV scenario, where 2-6 people communicate with each other with TV noise in the background. Our new tracks focus on audio-visual speaker diarization (AVSD), and audio-visual diarization and recognition (AVDR).

The 5th DNS Challenge aims to motivate development of DNS models with great speech quality in presence of reverberation, noise and interfering (neighboring) talkers. DNS has gained momentum given new trends of hybrid and remote work in a variety of daily-life scenarios. Improving speech quality reduce meeting fatigue and improve clarity of communication. 

Verbal communication in noisy environments can be hard. Speech enhancement using head-worn microphone arrays, such as hearing aids or augmented reality devices offers the opportunity to make it easier. However, the highly dynamic nature of the listening situation presents some challenges.