Blog
Recent headlines.
- Transcribing Lateral Podcast Episode 68: Diarization vs Manual Labels for 3+ Voices Oct 18, 2026
- Whisper vs Otter.ai 2026: WER vs DER on Low-Resource Calls Oct 15, 2026
- Smoother ASR Transcriptions: SVD Layers with Alpha ≥ 4 Cutoff Oct 12, 2026
- Why GPT-3's 175B Parameters Can't Transcribe: Choosing ASR by WER Oct 9, 2026
- Cisco Support Services 2026: 10% WER Threshold vs Speaker Diarization Oct 6, 2026
- Overlapping Speech Error Rates: Use 1—ASR Word Error Rate, Not Diarization Oct 3, 2026
- Podcast transcription errors 2026: $0.12 auto vs $1.79 human review Sep 30, 2026
- Speech Recognition Error Rates: Whisper Wins Off-Domain at Zero Labels Sep 27, 2026
- Overlapping Speech Transcription Errors: $0.25 Auto vs $1.50 Human Review Sep 24, 2026
- Overlapping speech in meetings: Two-pass stack cuts 29-31% vs single pass Sep 21, 2026
- Markov random fields: Structure learning I Sep 18, 2026
- Convert Video to Audio for Transcription: Mono WAV Cuts Word Error Rate 25% vs MP4 Sep 15, 2026
- Noisy field interviews: cut errors 38.2% to 15.1% with second mic Sep 12, 2026
- Interview Transcription Verbatim vs Clean 2026: $0.25 vs $1.79 Default AI Sep 9, 2026
- Human Transcription Cost: $0.80 vs $0.32 Hybrid When to Pay 2026 Sep 5, 2026
- 30s Truncation Trap: 27.3% to 11.8% cpWER Pyannote 3 Win Sep 4, 2026