Example 1 (p360, male speaker, at 6 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | HiFi-Codec | AudioDec | DAC | APCodec | MDCTCodec | |
Example 1 (p360, male speaker, at 9 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | AudioDec | DAC | APCodec | MDCTCodec | ||
Example 1 (p360, male speaker, at 12 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | HiFi-Codec | AudioDec | DAC | APCodec | MDCTCodec | |
Example 2 (p361, female speaker, at 6 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | HiFi-Codec | AudioDec | DAC | APCodec | MDCTCodec | |
Example 2 (p361, female speaker, at 9 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | AudioDec | DAC | APCodec | MDCTCodec | ||
Example 2 (p361, female speaker, at 12 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | HiFi-Codec | AudioDec | DAC | APCodec | MDCTCodec | |
Example 3 (p364, male speaker, at 6 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | HiFi-Codec | AudioDec | DAC | APCodec | MDCTCodec | |
Example 3 (p364, male speaker, at 9 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | AudioDec | DAC | APCodec | MDCTCodec | ||
Example 3 (p364, male speaker, at 12 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | HiFi-Codec | AudioDec | DAC | APCodec | MDCTCodec | |
Example 4 (s5, female speaker, at 6 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | HiFi-Codec | AudioDec | DAC | APCodec | MDCTCodec | |
Example 4 (s5, female speaker, at 9 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | AudioDec | DAC | APCodec | MDCTCodec | ||
Example 4 (s5, female speaker, at 12 kbps) |
|||||||
|---|---|---|---|---|---|---|---|
| Raw Audio | |||||||
| SoundStream | Encodec | HiFi-Codec | AudioDec | DAC | APCodec | MDCTCodec | |
Example 1 (p361, female speaker, at 6 kbps) |
|||||
|---|---|---|---|---|---|
| MDCTCodec | |||||
| w/o Melloss | w/o Qloss | w/o MDCTloss | rep. MRD | rep. MPD | |
Example 2 (p363, male speaker, at 6 kbps) |
|||||
|---|---|---|---|---|---|
| MDCTCodec | |||||
| w/o Melloss | w/o Qloss | w/o MDCTloss | rep. MRD | rep. MPD | |
Example 3 (p374, male speaker, at 6 kbps) |
|||||
|---|---|---|---|---|---|
| MDCTCodec | |||||
| w/o Melloss | w/o Qloss | w/o MDCTloss | rep. MRD | rep. MPD | |
Example 4 (s5, female speaker, at 6 kbps) |
|||||
|---|---|---|---|---|---|
| MDCTCodec | |||||
| w/o Melloss | w/o Qloss | w/o MDCTloss | rep. MRD | rep. MPD | |
(Results on VCTK dataset, 48 kHz, 6kbps)
Example 1 |
|||||
|---|---|---|---|---|---|
| Raw Audio | |||||
| DAC | APCodec | MDCTCodec | |||
Example 2 |
|||||
|---|---|---|---|---|---|
| Raw Audio | |||||
| DAC | APCodec | MDCTCodec | |||
(Results on CommonVoice dataset, 48 kHz, 6kbps)
Example 1 |
|||||
|---|---|---|---|---|---|
| Raw Audio | |||||
| DAC | APCodec | MDCTCodec | |||
Example 2 |
|||||
|---|---|---|---|---|---|
| Raw Audio | |||||
| DAC | APCodec | MDCTCodec | |||
(Results on Opencpop dataset, 48 kHz, 6kbps)
Example 1 |
|||||
|---|---|---|---|---|---|
| Raw Audio | |||||
| DAC | APCodec | MDCTCodec | |||
Example 2 |
|||||
|---|---|---|---|---|---|
| Raw Audio | |||||
| DAC | APCodec | MDCTCodec | |||
(Results on FSD50K dataset, 48 kHz, 6kbps)
Example 1 |
|||||
|---|---|---|---|---|---|
| Raw Audio | |||||
| DAC | APCodec | MDCTCodec | |||
Example 2 |
|||||
|---|---|---|---|---|---|
| Raw Audio | |||||
| DAC | APCodec | MDCTCodec | |||