引導式測驗 · 中等 等級
Mimi 串流音訊編解碼器測驗
查看 Mimi 的 12.5 Hz 令牌、語義和聲學密碼本、RVQ、因果流以及其編解碼器如何支援 Moshi 對話。
問題 1 的 8
哪個實驗室發表了 Mimi 和 Moshi 語音模型?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 哪個實驗室發表了 Mimi 和 Moshi 語音模型?
- 久泰
- OpenAI
- DeepMind
- Meta 人工智慧
- Mimi 每秒大約發出多少個代幣用於語音?
- 約200
- 約12.5
- 約1,000
- 約16,000
- Mimi 的第一個語義代碼本旨在表示什麼資訊?
- Only the waveform’s stereo channel count
- A transcript copied verbatim from a separate recognizer
- Semantic speech information distilled from WavLM representations
- The exact speaker identity with no acoustic tokens
- 為什麼咪咪被描述為“串流媒體”或“因果”?
- 它僅適用於串流音樂文件
- 它需要雲端流才能運行
- 它串流文字字幕
- 當音訊到達時它會發出令牌,而不是等待完整的剪輯
- Mimi 使用哪種量化技術來編碼音訊?
- 殘差向量量化 (RVQ)
- JPEG 塊壓縮
- 遊程編碼
- 主成分分析
- What does Mimi’s discrete audio-token representation let Moshi do?
- Treat audio tokens as ordinary words with identical meanings
- Model audio continuations as token sequences and decode them back into speech
- Avoid using an audio decoder
- Recover the original recording session stems
- What is a reported frame size for Mimi’s streaming codec in the Moshi paper?
- 8 seconds
- 1 millisecond
- 80 milliseconds
- 10分鐘
- Which encoder/decoder design does the Moshi report describe for Mimi?
- A text-only BERT encoder with no audio decoder
- A fixed lookup table with no learned encoder
- A bidirectional non-causal decoder that waits for the entire conversation
- Neural encoder and decoder Transformers with causal masking for streaming