We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We propose a novel approach to enable the use of large, single-speaker ASR models, such as Whisper, for target speaker ASR. The key claim of this method is that it is much easier to model relative differences among speakers by learning to condition on frame-level diarization outputs than to learn the space of all speaker embeddings. We find that adding even a single bias term per diarization output type before the first transformer block can transform single-speaker ASR models into target-speaker ASR models. Our approach also supports speaker-attributed ASR by sequentially generating transcripts for each speaker in a diarization output. This simplified method outperforms baseline speech separation and diarization cascade by 12.9 % absolute ORC-WER on the NOTSOFAR-1 dataset.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.09543")
get_code_for_paper("2409.09543")
have("2409.09543")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2409.09543.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2409.09543)
Connect an agent — have() is free.