Assessing the Impact of Noise and Speech Enhancement on the Intelligibility of Speech Codecs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913091029041152 |
|---|---|
| author | Behringer, Lyonel Leschanowsky, Anna Rajasekhar, Anjana Kratsch, Emily Fuchs, Guillaume |
| author_facet | Behringer, Lyonel Leschanowsky, Anna Rajasekhar, Anjana Kratsch, Emily Fuchs, Guillaume |
| contents | Preserving speech intelligibility is a minimum requirement for speech codecs in communication. Recently, very low-bitrate neural codecs have gained interest for replacing classical codecs, reinforcing the need to evaluate whether intelligibility is preserved in realistic scenarios. In this paper, we evaluate the intelligibility and listening effort of classical and neural speech codecs in clean and noisy conditions. Further, we assess the impact of speech enhancement (SE) before coding, simulating a possible audio processing pipeline. The results show that classical codecs are more noise robust than neural codecs. Further, SE can lead to significant intelligibility and listening effort improvements for codecs otherwise negatively affected by noise. Listening effort reveals nuanced differences when intelligibility is saturated. Lastly, objective intelligibility based on automatic speech recognition is highly correlated with subjective intelligibility scores averaged per condition. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03776 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Assessing the Impact of Noise and Speech Enhancement on the Intelligibility of Speech Codecs Behringer, Lyonel Leschanowsky, Anna Rajasekhar, Anjana Kratsch, Emily Fuchs, Guillaume Audio and Speech Processing Preserving speech intelligibility is a minimum requirement for speech codecs in communication. Recently, very low-bitrate neural codecs have gained interest for replacing classical codecs, reinforcing the need to evaluate whether intelligibility is preserved in realistic scenarios. In this paper, we evaluate the intelligibility and listening effort of classical and neural speech codecs in clean and noisy conditions. Further, we assess the impact of speech enhancement (SE) before coding, simulating a possible audio processing pipeline. The results show that classical codecs are more noise robust than neural codecs. Further, SE can lead to significant intelligibility and listening effort improvements for codecs otherwise negatively affected by noise. Listening effort reveals nuanced differences when intelligibility is saturated. Lastly, objective intelligibility based on automatic speech recognition is highly correlated with subjective intelligibility scores averaged per condition. |
| title | Assessing the Impact of Noise and Speech Enhancement on the Intelligibility of Speech Codecs |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2605.03776 |