13 March 2024 in IEEE Open Journal of Signal Processing
The ICASSP 2023 Acoustic Echo Cancellation Challenge is intended to stimulate research in acoustic echo cancellation (AEC), which is an important area of speech enhancement and is still a top issue in audio communication. This is the fourth AEC challenge and it is enhanced by adding a second track for personalized acoustic echo cancellation, reducing the algorithmic + buffering latency to 20 ms, as well as including a full-band version of AECMOS [1]. We open source two large datasets to train AEC models under both single talk and double talk scenarios. These datasets consist of recordings from more than 10,000 real audio devices and human speakers in real environments, as well as a synthetic dataset. We open source an online subjective test framework and provide an objective metric for researchers to quickly test their results. The winners of this challenge were selected based on the average mean opinion score (MOS) achieved across all scenarios and the word accuracy (WAcc) rate.
7 January 2025 in IEEE Open Journal of Signal Processing
The ICASSP 2024 Speech Signal Improvement Challenge aims to advance research in enhancing speech signal quality within communication systems. The speech signal quality can be assessed using the SIG metric from ITU-T P.835 and still remains a top issue in audio communication and conferencing systems. For example, in the ICASSP 2023 Deep Noise Suppression Challenge, the improvement in the background and overall quality is impressive, while the speech signal enhancement was not statistically significant. To improve the speech signal the following speech impairment areas must be addressed: coloration, discontinuity, loudness, reverberation, and noise. To this end, we organized ICASSP 2024 Speech Signal Improvement Challenge, which marks the second signal-focused challenge, built upon the success of the previous ICASSP 2023 Speech Signal Improvement Challenge. A training and test set was provided for the challenge, and the winners were determined using an extended crowdsourced implementation of ITU-T P.804's listening phase and the word accuracy (WAcc) rate. The results show that significant improvement was made across all measured dimensions of speech quality.
7 January 2025 in IEEE Open Journal of Signal Processing
Audio packet loss concealment hides gaps in VoIP audio streams caused by network packet loss. It operates in real-time with low computational requirements and latency, as demanded by modern communication systems. With the ICASSP 2024 Audio Deep Packet Loss Concealment Grand Challenge, we build on the success of the previous Audio PLC Challenge held at INTERSPEECH 2022. For the 2024 challenge at ICASSP, we update the challenge by introducing an overall harder blind evaluation set and extending the task from wideband to fullband audio, in keeping with current trends in internet telephony. In addition to the Word Accuracy metric, we also use a questionnaire based on an extension of ITU-T P.804 to more closely evaluate the performance of systems specifically on the PLC task. We evaluate a total of 9 systems submitted by different academic and industry teams, 8 of which satisfy the strict real-time performance requirements of the challenge, using both P.804 and Word Accuracy evaluations. Two systems share first place, with one of the systems having the advantage in terms of naturalness, while the other wins in terms of intelligibility. These systems are the current state of the art for Deep PLC.