Hello, I'm very interested in your job as a speech processing engineer, who has many R&D experiences in LVSR(large vocabulary speech recognition) with Kaldi, deep speech2, deep speech, google API, IBM Watson, pocketsphinx.
I've deployed many speech recognition applications as offline or streaming versions for many languages like English, Russian, French, Chinese, Spanish.
I've trained the model with various English accent data, so I've achieved 3.12% of WER for validation data of 3000 hours speech corpus.
I have full skill in the development of AI applications with Python, C++, Java on Windows, Linux, AWS.
I've provided C++, python binding, the web interface of speech recognition application with kaid, wav2letter.
I'm also very good at audio processing like speaker identification/verification/diarization, text to speech.
I hope to discuss more it with chat.
Thank you