The research team at IBM recently announced they’ve reached a new industry record at 5.5%, using the SWITCHBOARD linguistic corpus. This brings us closer to what’s considered to be the human error rate, 5.1%. They used deep learning technologies and acoustic models to accomplish this milestone.
The research team at IBM recently announced they’ve reached a new industry record in speech recognition with a word error rate of 5.5% using the SWITCHBOARD linguistic corpus. This brings it closer to what’s considered to be the human error rate of 5.1%. Humans typically miss one to two words out of every 20 words they hear. In a five-minute conversation, that could be as many as 80 words.
The research project includes applying deep learning technologies and incorporating acoustic models. The speech recognition model used Long Short Term Memory (LSTM) and WaveNet language models with a score fusion of three acoustic models.
