Projects per year
Speech coding is the most commonly used application of speech processing. Accumulated layers of improvements have however made codecs so complex that optimization of individual modules becomes increasingly difficult. This work introduces machine learning methodology to speech and audio coding, such that we can optimize quality in terms of overall entropy. We can then use conventional quantization, coding and perceptual models without modification such that the codec adheres to conventional requirements on algorithmic complexity, latency and robustness to packet loss. Experiments demonstrate that end-to-end optimization of quantization accuracy of the spectral envelope can be used for a lossless reduction in bitrate of 0.4 kbits/s.
|Title of host publication||Proceedings of Interspeech|
|Publication status||Published - Sep 2019|
|MoE publication type||A4 Article in a conference publication|
|Event||Interspeech - Graz, Austria|
Duration: 15 Sep 2019 → 19 Sep 2019
|Name||Interspeech - Annual Conference of the International Speech Communication Association|
|Period||15/09/2019 → 19/09/2019|
- speech and audio coding
- end-to-end optimization
- speech source modeling
FingerprintDive into the research topics of 'End-to-End Optimization of Source Models for Speech and Audio Coding Using a Machine Learning Framework'. Together they form a unique fingerprint.
- 1 Finished
Interdisciplinary research on statistical parametric speech synthesis
Alku, P., Nonavinakere Prabhakera, N., Bollepalli, B., Bäckström, T., Murtola, T., Airaksinen, M. & Juvela, L.
01/01/2018 → 31/12/2019
Project: Academy of Finland: Other research funding