SelanjutnyaPanduan berikutnya
Pemberian Tag Otomatis Musik
AI Audio
PANDUAN Audio AI
Listen, Attend and Spell (LAS) is a 2015 end-to-end speech-recognition model that maps acoustic filter-bank features to character sequences.
Dengarkan panduan iniDiceritakan oleh AI · ~2 min
Its Listener is a pyramidal recurrent encoder; its Speller is an attention-based recurrent decoder. The original paper reports results for a specific Google voice-search subset and does not establish that LAS outperformed the compared production system.
The LAS paper defines two components: a Listener, a pyramidal recurrent encoder that accepts filter-bank spectra, and a Speller, an attention-based recurrent decoder that emits characters. The pyramidal encoder reduces sequence length, making attention over the encoded frames more manageable. The paper describes joint learning of recognizer components and reports that its model generated character sequences without a pronunciation dictionary or a separately trained language model. On a subset of Google voice search, it reports 14.1% WER without a language model and 10.3% with language-model rescoring; the compared CLDNN-HMM result was 8.0%. These historical numbers apply to the paper’s specific evaluation.
Use LAS as a historical example of an encoder-decoder recognizer that emits characters from acoustic input.
Inspect how the pyramidal Listener reduces the length of the encoder sequence.
Trace how attention connects each Speller output step to encoder states.
Compare reported WER only within the paper’s stated task and evaluation setup.
LAS is useful historically for understanding attention-based end-to-end ASR. Later systems explored different encoders, objectives, and streaming mechanisms; performance and latency must be compared on the same data and decoding conditions.
Buletin gratis
Tiga cerita AI terverifikasi setiap pagi hari kerja, ditulis dalam bahasa Inggris sederhana. Gratis selamanya, tanpa iklan.
Satu email setiap hari kerja. Berhenti berlangganan dalam satu klik. Kami tidak pernah menjual atau membagikan alamat Anda.
Uji diri Anda sendiri
Umpan balik instan untuk setiap jawaban, dan sertifikat yang dapat dibagikan dengan ID yang dapat diverifikasi setelah Anda lulus kursus.
Mendukung pendidikan AI gratis. AI Understanding adalah organisasi nirlaba 501(c)(3) — tanpa iklan, tanpa paywall, selamanya. Berikan sumbangan
Listen, Attend and Spell (LAS) is a 2015 end-to-end speech-recognition model that maps acoustic filter-bank features to character sequences. Its Listener is a pyramidal recurrent encoder; its Speller is an attention-based recurrent decoder. The original paper reports results for a specific Google voice-search subset and does not establish that LAS outperformed the compared production system.
LAS terdiri dari encoder 'Listener' yang memproses audio dan decoder berbasis perhatian 'Speller' yang memancarkan karakter.
Speller adalah decoder yang menghasilkan transkripsi karakter demi karakter, mempelajari ejaan secara langsung.
Setiap lapisan BLSTM piramidal membagi dua panjang urutan, memperpendek urutan audio yang panjang sehingga perhatian dapat dilakukan secara komputasi.
Tidak seperti pipeline HMM-DNN klasik, LAS belajar langsung dari pasangan audio-ke-teks tanpa kamus fonem atau penyelarasan paksa.
Mekanisme perhatian menghitung bobot pada status encoder, membentuk vektor konteks yang digunakan decoder pada setiap langkah.
Teruslah belajar
Panduan lainnya dipilih untuk topik ini
SelanjutnyaPanduan berikutnya
Pemberian Tag Otomatis Musik
AI Audio