Language Modelling On Salmon
Metrics
Background (Domain) Consistency
Background (Random) Consistency
Background Alignment
Gender Consistency
Room Consistency
Sentiment Alignment
Sentiment Consistency
Speaker Consistency
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Background (Domain) Consistency | Background (Random) Consistency | Background Alignment | Gender Consistency | Room Consistency | Sentiment Alignment | Sentiment Consistency | Speaker Consistency |
|---|---|---|---|---|---|---|---|---|
| spirit-lm-interleaved-spoken-and-written | 55.0 | 64.0 | 59.5 | 85.0 | 54.5 | 52.0 | 73.5 | 81.0 |
| last-language-model-aware-speech-tokenization | 55.5 | 60.5 | 54.5 | 70.5 | 61.0 | 51.5 | 64.0 | 63.0 |
| textually-pretrained-speech-language-models | 55.5 | 60.5 | 56.5 | 69.5 | 59.0 | 53.0 | 61.5 | 69.0 |
| textually-pretrained-speech-language-models | 54.0 | 61.5 | 56.5 | 68.0 | 59.0 | 51.5 | 59.0 | 69.5 |
| text-free-prosody-aware-generative-spoken | 57.0 | 66.0 | 53.5 | 88.5 | 53.5 | 55.5 | 40.5 | 83.0 |
| last-language-model-aware-speech-tokenization | 56.0 | 61.0 | 53.0 | 68.5 | 62.5 | 53.5 | 65.0 | 64.5 |
| textually-pretrained-speech-language-models | 55.0 | 60.5 | 54.5 | 70.0 | 62.0 | 51.5 | 61.5 | 71.0 |
| spirit-lm-interleaved-spoken-and-written | 53.5 | 55.5 | 51.5 | 67.0 | 54.5 | 48.0 | 54.5 | 69.5 |