A new audit technique called ACES reveals that accent-discriminative information in speech recognition models concentrates in low-dimensional subspaces at early layers. Testing Wav2Vec2-base on five English accents, researchers found accent data clusters in layer 3 with just 8 dimensions, but attempting to remove it paradoxically worsens fairness.
Artificial Analysis has released an updated speech-to-text benchmark showing ElevenLabs and Google as top performers. The benchmark provides comparative analysis of current speech recognition systems across multiple models.
Apple researchers have identified a fundamental limitation in speech-adapted large language models: they consistently underperform their text-based counterparts on language understanding tasks. The team terms this the 'text-speech understanding gap' and documents that speech-adapted LLMs lag behind both their original text versions and cascaded speech-to-text pipelines.