liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
62 lines
15 KiB
XML
62 lines
15 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 780 480" width="780" height="480" style="background:#ffffff">
|
|
<defs><marker id="ah" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-light" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#999999"/></marker></defs>
|
|
<style>text { font-family: Arial, 'Apple SD Gothic Neo', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif !important; }</style>
|
|
|
|
<rect x="32" y="58" width="170" height="195" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="117" y="80" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">OpenAI Realtime</text>
|
|
<rect x="42" y="94" width="150" height="24" rx="3" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="117" y="106" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">gpt-realtime</text>
|
|
<text x="117" y="136" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">서버 측 VAD + 턴 감지</text>
|
|
<text x="117" y="158" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">비동기 함수 호출</text>
|
|
<text x="117" y="180" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">끼어들기: 현재 생성 중단</text>
|
|
<text x="117" y="200" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">본질은 여전히 VAD 프레임워크</text>
|
|
<text x="117" y="222" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11.5" fill="#999999" text-anchor="middle" dominant-baseline="central" font-weight="normal">2024 프리뷰 · GPT-4o 기반</text>
|
|
<rect x="214" y="58" width="170" height="195" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="299" y="80" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Gemini Live</text>
|
|
<rect x="224" y="94" width="150" height="24" rx="3" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="299" y="106" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">Gemini 2.0</text>
|
|
<text x="299" y="136" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">VAD 민감도 설정 가능</text>
|
|
<text x="299" y="158" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">끼어들어도 전송 정보 유지</text>
|
|
<text x="299" y="180" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">대화 일관성 최적화</text>
|
|
<text x="299" y="202" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">OpenAI와 유사한 전략</text>
|
|
<rect x="396" y="58" width="170" height="195" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
|
<text x="481" y="80" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Qwen3-Omni</text>
|
|
<rect x="406" y="94" width="150" height="24" rx="3" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="481" y="106" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">Thinker-Talker MoE</text>
|
|
<text x="481" y="136" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">사고(이해) + 표현(생성)</text>
|
|
<text x="481" y="158" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">다중 코드북 음성 인코딩</text>
|
|
<text x="481" y="180" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">첫 패킷 지연 234ms</text>
|
|
<text x="481" y="202" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">36개 중 22개 SOTA</text>
|
|
<rect x="578" y="58" width="170" height="195" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="663" y="80" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Step-Audio 2</text>
|
|
<rect x="588" y="94" width="150" height="24" rx="3" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="663" y="106" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="normal">잠재 오디오 인코딩 + RL</text>
|
|
<text x="663" y="136" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">종단 간 음성 토큰</text>
|
|
<text x="663" y="158" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">준언어 이해 83.09%</text>
|
|
<text x="663" y="180" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">CoT 사고 + RAG + 도구</text>
|
|
<text x="663" y="202" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Qwen2.5-Omni(44.18%)를 능가</text>
|
|
<rect x="40" y="273" width="700" height="100" rx="4" fill="#f5f5f5" stroke="#333333" stroke-width="2"/>
|
|
<text x="390" y="295" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">대부분 해법의 공통 한계: 여전히 턴 감지 메커니즘에 의존</text>
|
|
<text x="180" y="321" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">턴 감지의 한계</text>
|
|
<text x="180" y="341" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">사용자 멈춤 ≠ 발화 종료</text>
|
|
<text x="180" y="357" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">망설일 때 능동적 유도 필요</text>
|
|
<text x="400" y="321" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">단순한 끼어들기 판단</text>
|
|
<text x="400" y="341" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">"음", "네"는 맞장구 ≠ 끼어들기</text>
|
|
<text x="400" y="357" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">배경 소음을 발화로 오인</text>
|
|
<text x="620" y="321" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">근본 원인</text>
|
|
<text x="620" y="341" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">VAD는 음향 신호 기반</text>
|
|
<text x="620" y="357" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">의미 수준 정보 포착 불가</text>
|
|
<rect x="40" y="388" width="700" height="120" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
|
<text x="390" y="408" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">입력/출력 아키텍처 비교</text>
|
|
<text x="60" y="430" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">기존 직렬형</text>
|
|
<text x="210" y="430" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">오디오→VAD→ASR→텍스트→LLM→텍스트→TTS→오디오</text>
|
|
<text x="60" y="445" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">OpenAI/Gemini</text>
|
|
<text x="210" y="445" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">오디오→종단 간 모델(VAD 내장)→오디오/텍스트</text>
|
|
<text x="60" y="460" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">Qwen3-Omni</text>
|
|
<text x="210" y="460" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">오디오/이미지/동영상→Thinker(MoE)→Talker→음성 코덱</text>
|
|
<text x="60" y="475" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">Step-Audio 2</text>
|
|
<text x="210" y="475" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">원본 오디오→잠재 인코더→LLM+RL→오디오+텍스트 토큰</text>
|
|
<text x="60" y="491" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#333333" text-anchor="start" dominant-baseline="central" font-weight="bold">전이중 Moshi</text>
|
|
<text x="210" y="491" font-family="Arial, 'Apple SD Gothic Neo', 'Noto Sans CJK KR', 'Noto Sans KR', 'Malgun Gothic', 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="11" fill="#666666" text-anchor="start" dominant-baseline="central" font-weight="normal">병렬 이중 오디오 스트림 + 내적 독백 텍스트 스트림 → VAD / 턴 감지 불필요</text>
|
|
</svg>
|
